Search Results for author:
Found 151 papers, 51 papers with code
The ManDi Corpus: A Spoken Corpus of Mandarin Regional Dialects
In the present paper, we introduce the ManDi Corpus, a spoken corpus of regional Mandarin dialects and Standard Mandarin.
DreamLLM: Synergistic Multimodal Comprehension and Creation
This paper presents DreamLLM, a learning framework that first achieves versatile Multimodal Large Language Models (MLLMs) empowered with frequently overlooked synergy between multimodal comprehension and creation.
Improving Open Information Extraction with Large Language Models: A Study on Demonstration Uncertainty
Open Information Extraction (OIE) task aims at extracting structured facts from unstructured text, typically in the form of (subject, relation, object) triples.
Helper Recommendation with seniority control in Online Health Community
Online health communities (OHCs) are forums where patients with similar conditions communicate their experiences and provide moral support.
Benchmarking Robustness and Generalization in Multi-Agent Systems: A Case Study on Neural MMO
We present the results of the second Neural MMO challenge, hosted at IJCAI 2022, which received 1600+ submissions.
Feature Attention Network (FA-Net): A Deep-Learning Based Approach for Underwater Single Image Enhancement
In particular, we propose a Residual Feature Attention Block (RFAB), containing the channel attention, pixel attention, and residual learning mechanism with long and short skip connections.
Staleness-Alleviated Distributed GNN Training via Online Dynamic-Embedding Prediction
It utilizes an offline memory to cache historical information (e. g., node embedding) as an affordable approximation of the exact value and achieves high concurrency.
ChatSpot: Bootstrapping Multimodal LLMs via Precise Referring Instruction Tuning
Based on precise referring instruction, we propose ChatSpot, a unified end-to-end multimodal large language model that supports diverse forms of interactivity including mouse clicks, drag-and-drop, and drawing boxes, which provides a more flexible and seamless interactive experience.
Designing a Direct Feedback Loop between Humans and Convolutional Neural Networks through Local Explanations
To mitigate the gap, we designed DeepFuse, the first interactive design that realizes the direct feedback loop between a user and CNNs in diagnosing and revising CNN's vulnerability using local explanations.
Leveraging GPT-4 for Food Effect Summarization to Enhance Product-Specific Guidance Development via Iterative Prompting
Specifically, we propose a three-turn iterative prompting approach to food effect summarization in which the keyword-focused and length-controlled prompts are respectively provided in consecutive turns to refine the quality of the generated summary.
A Survey on Knowledge Graphs for Healthcare: Resources, Applications, and Promises
Healthcare knowledge graphs (HKGs) have emerged as a promising tool for organizing medical knowledge in a structured and interpretable way, which provides a comprehensive view of medical concepts and their relationships.
TKDP: Threefold Knowledge-enriched Deep Prompt Tuning for Few-shot Named Entity Recognition
Few-shot named entity recognition (NER) exploits limited annotated instances to identify named mentions.
JGAT: a joint spatio-temporal graph attention model for brain decoding
However, traditional approaches for integrating FC and SC overlook the dynamical variations, which stand a great chance to over-generalize the brain neural network.
Graph Neural Network for spatiotemporal data: methods and applications
Graph neural networks (GNNs) have emerged as a powerful tool for modeling and understanding data with dependencies to each other such as spatial and temporal dependencies.
Domain Specialization as the Key to Make Large Language Models Disruptive: A Comprehensive Survey
In this article, we present a comprehensive survey on domain specification techniques for large language models, an emerging direction critical for large language model applications.
Domain Generalization Deep Graph Transformation
As a result, domain generalization graph transformation that predicts graphs not available in the training data is under-explored, with multiple key challenges to be addressed including (1) the extreme space complexity when training on all input-output mode combinations, (2) difference of graph topologies between the input and the output modes, and (3) how to generalize the model to (unseen) target domains that are not in the training data.
Deep Graph Representation Learning and Optimization for Influence Maximization
Influence maximization (IM) is formulated as selecting a set of initial users from a social network to maximize the expected number of influenced users.
Molecular Design Based on Integer Programming and Splitting Data Sets by Hyperplanes
A novel framework for designing the molecular structure of chemical compounds with a desired chemical property has recently been proposed.
Dealing With Heterogeneous 3D MR Knee Images: A Federated Few-Shot Learning Method With Dual Knowledge Distillation
The supervised learning of the proposed method extracts features from limited labeled data in each client, while the unsupervised data is used to distill both feature and response-based knowledge from a national data repository to further improve the accuracy of the collaborative model and reduce the communication cost.
Knowledge-enhanced Neural Machine Reasoning: A Review
Knowledge-enhanced neural machine reasoning has garnered significant attention as a cutting-edge yet challenging research area with numerous practical applications.
Saliency-Augmented Memory Completion for Continual Learning
Specifically, we innovatively propose to store the part of the image most important to the tasks in episodic memory by saliency map extraction and memory encoding.
Going Beyond XAI: A Systematic Survey for Explanation-Guided Learning
As the societal impact of Deep Neural Networks (DNNs) grows, the goals for advancing DNNs become more complex and diverse, ranging from improving a conventional model accuracy metric to infusing advanced human virtues such as fairness, accountability, transparency (FaccT), and unbiasedness.
Explainable artificial intelligence
Explainable Artificial Intelligence (XAI)
+1
DeepGAR: Deep Graph Learning for Analogical Reasoning
As the most well-known computational method of analogical reasoning, Structure-Mapping Theory (SMT) abstracts both target and base subjects into relational graphs and forms the cognitive process of analogical reasoning by finding a corresponding subgraph (i. e., correspondence) in the target graph that is aligned with the base graph.
3DFill:Reference-guided Image Inpainting by Self-supervised 3D Image Alignment
We then fill the hole in the target image with the contents of the aligned image.
TOE: A Grid-Tagging Discontinuous NER Model Enhanced by Embedding Tag/Word Relations and More Fine-Grained Tags
Concretely, we construct tag representations and embed them into TREM, so that TREM can treat tag and word representations as queries/keys/values and utilize self-attention to model their relationships.
Deep Spatial Domain Generalization
Spatial domain generalization is a spatial extension of domain generalization, which can generalize to unseen spatial domains in continuous 2D space.
Multi-objective Deep Data Generation with Correlated Property Control
Developing deep generative models has been an emerging field due to the ability to model and generate complex data for various purposes, such as image synthesis and molecular design.
Molecular Design Based on Integer Programming and Quadratic Descriptors in a Two-layered Model
A set of graph theoretical descriptors in the feature function plays a key role to derive a compact formulation of such an MILP.
OneEE: A One-Stage Framework for Fast Overlapping and Nested Event Extraction
Event extraction (EE) is an essential task of information extraction, which aims to extract structured event information from unstructured text.
Two-Stage Fine-Tuning: A Novel Strategy for Learning Class-Imbalanced Data
Owing to this paucity of samples, learning on the tail classes is especially challenging for the fine-tuning when transferring a pretrained model to a downstream task.
Controllable Data Generation by Deep Learning: A Review
Finally, the promising future directions of controllable deep data generation are highlighted and five potential challenges are identified.
Saliency-Regularized Deep Multi-Task Learning
Specifically, we propose to model the task relation as the similarity between task input gradients, with a theoretical analysis of their equivalency.
RES: A Robust Framework for Guiding Visual Explanation
Despite the fast progress of explanation techniques in modern Deep Neural Networks (DNNs) where the main focus is handling "how to generate the explanations", advanced research questions that examine the quality of the explanation itself (e. g., "whether the explanations are accurate") and improve the explanation quality (e. g., "how to adjust the model to generate more accurate explanations when explanations are inaccurate") are still relatively under-explored.
Source Localization of Graph Diffusion via Variational Autoencoders for Graph Inverse Problems
Different from most traditional source localization methods, this paper focuses on a probabilistic manner to account for the uncertainty of different candidate sources.
An Invertible Graph Diffusion Neural Network for Source Localization
This paper aims to establish a generic framework of invertible graph diffusion models for source localization on graphs, namely Invertible Validity-aware Graph Diffusion (IVGD), to handle major challenges including 1) Difficulty to leverage knowledge in graph diffusion models for modeling their inverse processes in an end-to-end fashion, 2) Difficulty to ensure the validity of the inferred sources, and 3) Efficiency and scalability in source inference.
Distributed Graph Neural Network Training with Periodic Stale Representation Synchronization
Traditional sampling-based methods accelerate GNN training by dropping edges and nodes, which impairs the graph integrity and model performance.
Temporal Domain Generalization with Drift-Aware Dynamic Neural Networks
Temporal domain generalization is a promising yet extremely challenging area where the goal is to learn models under temporally changing data distributions and generalize to unseen data distributions following the trends of the change.
Stability of China's Stock Market: Measure and Forecast by Ricci Curvature on Network
As far as we know, this is the first paper to apply Ricci curvature to forecast the systemic stability of domestic stock market, and our results show that Ricci curvature has good explanatory power for the market stability and can be a good indicator to judge the future risk and volatility of the domestic market.
Logit Normalization for Long-tail Object Detection
Real-world data exhibiting skewed distributions pose a serious challenge to existing object detectors.
Task-specific Inconsistency Alignment for Domain Adaptive Object Detection
To address this issue, in this paper, we propose Task-specific Inconsistency Alignment (TIA), by developing a new alignment mechanism in separate task spaces, improving the performance of the detector on both subtasks.
Disentangled Spatiotemporal Graph Generative Models
Spatiotemporal graph represents a crucial data structure where the nodes and edges are embedded in a geometric space and can evolve dynamically over time.
Interpretable Molecular Graph Generation via Monotonic Constraints
Recent advances in deep graph generative models treat molecule design as graph generation problems which provide new opportunities toward the breakthrough of this long-lasting problem.
Black-box Node Injection Attack for Graph Neural Networks
Graph Neural Networks (GNNs) have drawn significant attentions over the years and been broadly applied to vital fields that require high security standard such as product recommendation and traffic forecasting.
Aligning Eyes between Humans and Deep Neural Network through Interactive Attention Alignment
We propose a novel framework of Interactive Attention Alignment (IAA) that aims at realizing human-steerable Deep Neural Networks (DNNs).
Deep Generative Model for Periodic Graphs
To address them, this paper proposes Periodical-Graph Disentangled Variational Auto-encoder (PGD-VAE), a new deep generative models for periodic graphs that can automatically learn, disentangle, and generate local and global graph patterns.
Efficiently Disentangle Causal Representations
This paper proposes an efficient approach to learning disentangled representations with causal mechanisms based on the difference of conditional probabilities in original and new distributions.
Do Multi-Lingual Pre-trained Language Models Reveal Consistent Token Attributions in Different Languages?
During the past several years, a surge of multi-lingual Pre-trained Language Models (PLMs) has been proposed to achieve state-of-the-art performance in many cross-lingual downstream tasks.
A Convergent ADMM Framework for Efficient Neural Network Training
As a well-known optimization framework, the Alternating Direction Method of Multipliers (ADMM) has achieved tremendous success in many classification and regression applications.
Adaptive Kernel Graph Neural Network
To solve this problem, in this paper, we propose a novel framework - i. e., namely Adaptive Kernel Graph Neural Network (AKGNN) - which learns to adapt to the optimal graph kernel in a unified manner at the first attempt.
Zero-Shot Cross-Lingual Machine Reading Comprehension via Inter-sentence Dependency Graph
We target the task of cross-lingual Machine Reading Comprehension (MRC) in the direct zero-shot setting, by incorporating syntactic features from Universal Dependencies (UD), and the key features we use are the syntactic relations within each sentence.
Representation Learning on Spatial Networks
Specifically, a provably information-lossless and roto-translation invariant representation of spatial information on networks is presented.
KNAS: Green Neural Architecture Search
Many existing neural architecture search (NAS) solutions rely on downstream training for architecture evaluation, which takes enormous computations.
Heterogeneous Temporal Graph Neural Network
To retain the heterogeneity, intra-relation aggregation is first performed over each slice of HTG to attentively aggregate information of neighbors with the same type of relation, and then intra-relation aggregation is exploited to gather information over different types of relations; to handle temporal dependencies, across-time aggregation is conducted to exchange information across different graph slices over the HTG.
GraphGT: Machine Learning Datasets for Graph Generation and Transformation
Graph generation, which learns from known graphs and discovers novel graphs, has great potential in numerous research topics like drug design and mobility synthesis and is one of the fastest-growing domains recently due to its promise for discovering new knowledge.
A Method for Inferring Polymers Based on Linear Regression and Integer Programming
For this, we introduce a new way of representing a polymer as a form of monomer and define new descriptors that feature the structure of polymers.
Molecular Design Based on Artificial Neural Networks, Integer Programming and Grid Neighbor Search
In the framework, a chemical graph with a target chemical value is inferred as a feasible solution of a mixed integer linear program that represents a prediction function and other requirements on the structure of graphs.
Long-term, Short-term and Sudden Event: Trading Volume Movement Prediction with Graph-based Multi-view Modeling
Trading volume movement prediction is the key in a variety of financial applications.
Communication Efficiency in Federated Learning: Achievements and Challenges
Over the years, this has become an emerging technology especially with various data protection and privacy policies being imposed FL allows performing machine learning tasks whilst adhering to these challenges.
Bridging the Gap between Spatial and Spectral Domains: A Unified Framework for Graph Neural Networks
Deep learning's performance has been extensively recognized recently.
An Inverse QSAR Method Based on Linear Regression and Integer Programming
In the framework, we first define a feature vector $f(C)$ of a chemical graph $C$ and construct an ANN that maps $x=f(C)$ to a predicted value $\eta(x)$ of a chemical property $\pi$ to $C$.
RefBERT: Compressing BERT by Referencing to Pre-computed Representations
Differently, in this paper, we propose RefBERT to leverage the knowledge learned from the teacher, i. e., facilitating the pre-computed BERT representation on the reference sample and compressing BERT into a smaller student model.
Transition behavior of the seizure dynamics modulated by the astrocyte inositol triphosphate noise
Our simulation results show that the increase of the IP3 noise intensity induces the depolarization-block epileptic seizures together with an increase in neuronal firing frequency.
DSR: Direct Simultaneous Registration for Multiple 3D Images
This paper presents a novel algorithm named Direct Simultaneous Registration (DSR) that registers a collection of 3D images in a simultaneous fashion without specifying any reference image, feature extraction and matching, or information loss or reuse.
Towards Quantized Model Parallelism for Graph-Augmented MLPs Based on Gradient-Free ADMM Framework
Theoretical convergence to a (quantized) stationary point of the pdADMM-G algorithm and the pdADMM-G-Q algorithm is provided with a sublinear convergence rate $o(1/k)$, where $k$ is the number of iterations.
Schematic Memory Persistence and Transience for Efficient and Robust Continual Learning
However, since forgetting is inevitable given bounded memory and unbounded task loads, 'how to reasonably forget' is a problem continual learning must address in order to reduce the performance gap between AIs and humans, in terms of 1) memory efficiency, 2) generalizability, and 3) robustness when dealing with noisy data.
Cyber Intrusion Detection by Using Deep Neural Networks with Attack-sharing Loss
To achieve high detection accuracy on imbalanced data, we design a novel attack-sharing loss function that can effectively move the decision boundary towards the attack classes and eliminates the bias towards the majority/benign class.
Interpretable Distance Metric Learning for Handwritten Chinese Character Recognition
In this paper, we propose an interpretable distance metric learning approach for handwritten Chinese character recognition.
Sign-regularized Multi-task Learning
Multi-task learning is a framework that enforces different learning tasks to share their knowledge to improve their generalization performance.
GP: Context-free Grammar Pre-training for Text-to-SQL Parsers
A new method for Text-to-SQL parsing, Grammar Pre-training (GP), is proposed to decode deep relations between question and database.
FamDroid: Learning-Based Android Malware Family Classification Using Static Analysis
At present, the main problem of existing research works on Android malware family classification lies in that the extracted features are inadequate to represent the common behavior characteristics of the malware in malicious families, and leveraging a single classifier or a static ensemble classifier is restricted to further improve the accuracy of classification.
Malware Detection
Cryptography and Security
A Gradient-based Kernel Approach for Efficient Network Architecture Search
Inspired by our new finding, we explore a simple yet effective network architecture search (NAS) approach that leverages gradient correlation and gradient values to find well-performing architectures.
Gradient Descent Resists Compositionality
In this paper, we argue that gradient descent is one of the reasons that make compositionality learning hard during neural network optimization.
Transferability of Compositionality
To our best knowledge, this is the first work to focus on the transferability of compositionality, and it is orthogonal to existing efforts of learning compositional representations in training distribution.
Property Controllable Variational Autoencoder via Invertible Mutual Dependence
Deep generative models have made important progress towards modeling complex, high dimensional data via learning latent representations.
XLP at SemEval-2020 Task 9: Cross-lingual Models with Focal Loss for Sentiment Analysis of Code-Mixing Language
In this paper, we present an approach for sentiment analysis in code-mixed language on twitter defined in SemEval-2020 Task 9.
pdADMM: parallel deep learning Alternating Direction Method of Multipliers
In this paper, we propose a novel parallel deep learning ADMM framework (pdADMM) to achieve layer parallelism: parameters in each layer of neural networks can be updated independently in parallel.
Online Decision Trees with Fairness
In this paper, we propose a novel framework of online decision tree with fairness in the data stream with possible distribution drifting.
Disentangled Dynamic Graph Deep Generation
Extending existing deep generative models from static to dynamic graphs is a challenging task, which requires to handle the factorization of static and dynamic characteristics as well as mutual interactions among node and edge patterns.
FedAT: A High-Performance and Communication-Efficient Federated Learning System with Asynchronous Tiers
By bridging the synchronous and asynchronous training through tiering, FedAT minimizes the straggler effect with improved convergence speed and test accuracy.
A new network-base high-level data classification methodology (Quipus) by modeling attribute-attribute interactions
The current results show us that this approach improves the accuracy of the high-level classification algorithm based on betweenness centrality.
Graph-based Multi-hop Reasoning for Long Text Generation
The reasoning module is responsible for searching skeleton paths from a knowledge graph to imitate the imagination process in the human writing for semantic transfer.
A Novel Method for Inference of Acyclic Chemical Compounds with Bounded Branch-height Based on Artificial Neural Networks and Integer Programming
In the second phase, given a target value $y^*$ of property $\pi$, a feature vector $x^*$ is inferred by solving an MILP formulated from the trained ANN so that $\psi(x^*)$ is close to $y^*$ and then a set of chemical structures $G^*$ such that $f(G^*)= x^*$ is enumerated by a graph search algorithm.
Data Structures and Algorithms Computational Engineering, Finance, and Science 05C92, 92E10, 05C30, 68T07, 90C11, 92-04
Factorized Deep Generative Models for Trajectory Generation with Spatiotemporal-Validity Constraints
Inspired by the success of deep generative neural networks for images and texts, a fast-developing research topic is deep generative models for trajectory data which can learn expressively explanatory models for sophisticated latent patterns.
A Network-Based High-Level Data Classification Algorithm Using Betweenness Centrality
Data classification is a major machine learning paradigm, which has been widely applied to solve a large number of real-world problems.
Tunable Subnetwork Splitting for Model-parallelism of Neural Network Training
In this paper, we analyze the reason and propose to achieve a compelling trade-off between parallelism and accuracy by a reformulation called Tunable Subnetwork Splitting Method (TSSM), which can tune the decomposition granularity of deep neural networks.
Event Prediction in the Big Data Era: A Systematic Survey
This paper aims to provide a systematic and comprehensive survey of the technologies, applications, and evaluations of event prediction in the big data era.
A Systematic Survey on Deep Generative Models for Graph Generation
Graphs are important data representations for describing objects and their relationships, which appear in a wide diversity of real-world scenarios.
Interpretable Deep Graph Generation with Node-Edge Co-Disentanglement
Disentangled representation learning has recently attracted a significant amount of attention, particularly in the field of image representation learning.
TG-GAN: Continuous-time Temporal Graph Generation with Deep Generative Models
The recent deep generative models for static graphs that are now being actively developed have achieved significant success in areas such as molecule design.
Compositional Language Continual Learning
It also shows significant improvement in machine translation task.
Spatiotemporal data analysis with chronological networks
In this paper, we propose a network-based model for spatiotemporal data analysis called chronnet.
Generating Tertiary Protein Structures via an Interpretative Variational Autoencoder
Much scientific enquiry across disciplines is founded upon a mechanistic treatment of dynamic systems that ties form to function.
Dynamic Reconstruction of Deformable Soft-tissue with Stereo Scope in Minimal Invasive Surgery
Our SLAM system can: (1) Incrementally build a live model by progressively fusing new observations with vivid accurate texture.
Dynamic Reconstruction
Simultaneous Localization and Mapping
Deep Multi-attributed Graph Translation with Node-Edge Co-evolution
Then, a spectral graph regularization based on our non-parametric graph Laplacian is proposed in order to learn and maintain the consistency of the predicted nodes and edges.
Bridging the Gap between Spatial and Spectral Domains: A Survey on Graph Neural Networks
Deep learning's success has been widely recognized in a variety of machine learning tasks, including image classification, audio recognition, and natural language processing.
Chaotic Phase Synchronization and Desynchronization in an Oscillator Network for Object Selection
Oscillators in the network representing the salient object in a given scene are phase synchronized, while no phase synchronization occurs for background objects.
Particle Competition and Cooperation for Semi-Supervised Learning with Label Noise
Computer simulations show the classification accuracy of the proposed method when applied to some artificial and real-world data sets, in which we introduce increasing amounts of label noise.
Code-Bridged Classifier (CBC): A Low or Negative Overhead Defense for Making a CNN Classifier Robust Against Adversarial Attacks
In this paper, we propose Code-Bridged Classifier (CBC), a framework for making a Convolutional Neural Network (CNNs) robust against adversarial attacks without increasing or even by decreasing the overall models' computational complexity.
Automated Analysis of Femoral Artery Calcification Using Machine Learning Techniques
We report an object tracking algorithm that combines geometrical constraints, thresholding, and motion detection for tracking of the descending aorta and the network of major arteries that branch from the aorta including the iliac and femoral arteries.
Learning to Recommend via Meta Parameter Partition
The fixed part, capturing user invariant features, is shared by all users and is learned during offline meta learning stage.
Scalable Global Alignment Graph Kernel Using Random Features: From Node Embedding to Graph Embedding
In particular, RGE is shown to achieve \emph{(quasi-)linear scalability} with respect to the number and the size of the graphs.
Efficient Global String Kernel with Random Features: Beyond Counting Substructures
In this paper, we present a new class of global string kernels that aims to (i) discover global properties hidden in the strings through global alignments, (ii) maintain positive-definiteness of the kernel, without introducing a diagonal dominant kernel matrix, and (iii) have a training cost linear with respect to not only the length of the string but also the number of training string samples.
TITAN: A Spatiotemporal Feature Learning Framework for Traffic Incident Duration Prediction
In this paper, we propose a traffic incident duration prediction model that simultaneously predicts the impact of the traffic incidents and identifies the critical groups of temporal features via a multi-task learning framework.
LexicalAT: Lexical-Based Adversarial Reinforcement Training for Robust Sentiment Classification
The generator learns to generate examples to attack the classifier while the classifier learns to defend these attacks.
Compositional Generalization for Primitive Substitutions
Compositional generalization is a basic mechanism in human language learning, but current neural networks lack such ability.
BEAN: Interpretable Representation Learning with Biologically-Enhanced Artificial Neuronal Assembly Regularization
Deep neural networks (DNNs) are known for extracting useful information from large amounts of data.
Gradient-free Neural Network Training by Multi-convex Alternating Optimization
To overcome these drawbacks, alternating minimization-based methods for deep neural network optimization have attracted fast-increasing attention recently.
DEEP GRAPH SPECTRAL EVOLUTION NETWORKS FOR GRAPH TOPOLOGICAL TRANSFORMATION
On the other hand, graph topological evolution has been investigated in the graph signal processing domain historically, but it involves intensive labors to manually determine suitable prescribed spectral models and prohibitive difficulty to fit their potential combinations and compositions.
Multi-stage Deep Classifier Cascades for Open World Recognition
At present, object recognition studies are mostly conducted in a closed lab setting with classes in test phase typically in training phase.
DynGraph2Seq: Dynamic-Graph-to-Sequence Interpretable Learning for Health Stage Prediction in Online Health Forums
In this paper, we first formulate the transition of user activities as a dynamic graph with multi-attributed nodes, then formalize the health stage inference task as a dynamic graph-to-sequence learning problem, and hence propose a novel dynamic graph-to-sequence neural networks architecture (DynGraph2Seq) to address all the challenges.
CBOWRA: A Representation Learning Approach for Medication Anomaly Detection
Electronic health record is an important source for clinical researches and applications, and errors inevitably occur in the data, which could lead to severe damages to both patients and hospital services.
Pyramid: Machine Learning Framework to Estimate the Optimal Timing and Resource Usage of a High-Level Synthesis Design
HLS tools offer a plethora of techniques to optimize designs for both area and performance, but resource usage and timing reports of HLS tools mostly deviate from the post-implementation results.
Efficient two step optimization for large embedded deformation graph based SLAM
In this paper, we propose an approach to decouple nodes of deformation graph in large scale dense deformable SLAM and keep the estimation time to be constant.
CUR Low Rank Approximation of a Matrix at Sublinear Cost
Low rank approximation of a matrix (hereafter LRA) is a highly important area of Numerical Linear and Multilinear Algebra and Data Mining and Analysis.
Numerical Analysis Numerical Analysis
ADMM for Efficient Deep Learning with Global Convergence
However, as an emerging domain, several challenges remain, including 1) The lack of global convergence guarantees, 2) Slow convergence towards solutions, and 3) Cubic time complexity with regard to feature dimensions.
Interpreting and Evaluating Neural Network Robustness
Recently, adversarial deception becomes one of the most considerable threats to deep neural networks.
iRDA Method for Sparse Convolutional Neural Networks
We propose a new approach, known as the iterative regularized dual averaging (iRDA), to improve the efficiency of convolutional neural networks (CNN) by significantly reducing the redundancy of the model without reducing its accuracy.
Learning Good Representation via Continuous Attention
In this paper we present our scientific discovery that good representation can be learned via continuous attention during the interaction between Unsupervised Learning(UL) and Reinforcement Learning(RL) modules driven by intrinsic motivation.
Global Fire Season Severity Analysis and Forecasting
In this paper, we evaluate the possibility of using historical data from 2003 to 2017 of active fire detections (NASA's MODIS MCD14ML C6) and time series forecasting methods to estimate global fire season severity (FSS), here defined as the accumulated fire detections in a season.
Applications
CircConv: A Structured Convolution with Low Complexity
Deep neural networks (DNNs), especially deep convolutional neural networks (CNNs), have emerged as the powerful technique in various machine learning applications.
Estimating the Circuit Deobfuscating Runtime based on Graph Deep Learning
Deobfuscation runtime could have a large span ranging from few milliseconds to thousands of years or more, depending on the number and layouts of the ICs and camouflaged gates.
The Effect of Time Series Distance Functions on Functional Climate Networks
In this context, functional climate networks can be constructed using a spatiotemporal climate dataset and a suitable time series distance function.
Data Analysis, Statistics and Probability Atmospheric and Oceanic Physics
Robust Regression via Online Feature Selection under Adversarial Data Corruption
The presence of data corruption in user-generated streaming data, such as social media, motivates a new fundamental problem that learns reliable regression coefficient when features are not accessible entirely at one time.
WALL-E: An Efficient Reinforcement Learning Research Framework
There are two halves to RL systems: experience collection time and policy learning time.
From Node Embedding to Graph Embedding: Scalable Global Graph Kernel via Random Features
Graph kernels are one of the most important methods for graph data analysis and have been successfully applied in diverse applications.
Identifying the Best Machine Learning Algorithms for Brain Tumor Segmentation, Progression Assessment, and Overall Survival Prediction in the BRATS Challenge
This study assesses the state-of-the-art machine learning (ML) methods used for brain tumor image analysis in mpMRI scans, during the last seven instances of the International Brain Tumor Segmentation (BraTS) challenge, i. e., 2012-2018.
Interpreting Adversarial Robustness: A View from Decision Surface in Input Space
One popular hypothesis of neural network generalization is that the flat local minima of loss surface in parameter space leads to good generalization.
Organ at Risk Segmentation in Head and Neck CT Images by Using a Two-Stage Segmentation Framework Based on 3D U-Net
Accurate segmentation of organ at risk (OAR) play a critical role in the treatment planning of image guided radiation treatment of head and neck cancer.
Source-Critical Reinforcement Learning for Transferring Spoken Language Understanding to a New Language
This paper focuses on the language transferring task given a tiny in-domain parallel SLU corpus.
Cultural Vocal Bursts Intensity Prediction
General Classification
+5
Source Critical Reinforcement Learning for Transferring Spoken Language Understanding to a New Language
An SLU corpus is a monolingual corpus with domain/intent/slot labels.
Cultural Vocal Bursts Intensity Prediction
General Classification
+6
Make $\ell_1$ Regularization Effective in Training Sparse CNN
Compressed Sensing using $\ell_1$ regularization is among the most powerful and popular sparsification technique in many applications, but why has it not been used to obtain sparse deep learning model such as convolutional neural network (CNN)?
Distributed Self-Paced Learning in Alternating Direction Method of Multipliers
One key issue in SPL is the training process required for each instance weight depends on the other samples and thus cannot easily be run in a distributed manner in a large-scale dataset.
Learning to Explore via Meta-Policy Gradient
The performance of off-policy learning, including deep Q-learning and deep deterministic policy gradient (DDPG), critically depends on the choice of the exploration policy.
Deep Graph Translation
To achieve this, we propose a novel Graph-Translation-Generative Adversarial Networks (GT-GAN) which will generate a graph translator from input to target graphs.
On the Universal Approximation Property and Equivalence of Stochastic Computing-based Neural Networks and Binary Neural Networks
Based on the universal approximation property, we further prove that SCNNs and BNNs exhibit the same energy complexity.
Learning to Explore with Meta-Policy Gradient
The performance of off-policy learning, including deep Q-learning and deep deterministic policy gradient (DDPG), critically depends on the choice of the exploration policy.
MIS-SLAM: Real-time Large Scale Dense Deformable SLAM System in Minimal Invasive Surgery Based on Heterogeneous Computing
Idled CPU is used to perform ORB- SLAM for providing robust global pose.
Occlusion Aware Unsupervised Learning of Optical Flow
Especially on KITTI dataset where abundant unlabeled samples exist, our unsupervised method outperforms its counterpart trained with supervised learning.
Latent Dirichlet Allocation (LDA) and Topic modeling: models, applications, a survey
Topic modeling is one of the most powerful techniques in text mining for data mining, latent data discovery, and finding relationships among data, text documents.
Unsupervised Learning of Geometry with Edge-aware Depth-Normal Consistency
Learning to reconstruct depths in a single image by watching unlabeled videos via deep convolutional network (DCN) is attracting significant attention in recent years.
Feature learning in feature-sample networks using multi-objective optimization
We show that the enhanced network contains more information and can be exploited to improve the performance of machine learning methods.
Online and Distributed Robust Regressions under Adversarial Data Corruption
In today's era of big data, robust least-squares regression becomes a more challenging problem when considering the adversarial corruption along with explosive growth of datasets.
A Generic Framework for Interesting Subspace Cluster Detection in Multi-attributed Networks
As a case study, we specialize SG-Pursuit to optimize a number of well-known score functions for two typical tasks, including detection of coherent dense and anomalous connected subspace clusters in real-world networks.
Unsupervised Learning Layers for Video Analysis
This paper presents two unsupervised learning layers (UL layers) for label-free video analysis: one for fully connected layers, and the other for convolutional ones.
Nonconvex Generalization of Alternating Direction Method of Multipliers for Nonlinear Equality Constrained Problems
The classic Alternating Direction Method of Multipliers (ADMM) is a popular framework to solve linear-equality constrained problems.
Optimization and Control Social and Information Networks
Theoretical Properties for Neural Networks with Weight Matrices of Low Displacement Rank
Recently low displacement rank (LDR) matrices, or so-called structured matrices, have been proposed to compress large-scale neural networks.
Network Unfolding Map by Edge Dynamics Modeling
Labeled vertices generate new particles that compete against rival particles for edge domination.
Time Series Clustering via Community Detection in Networks
In this paper, we propose a technique for time series clustering using community detection in complex networks.
A feasible roadmap for developing volumetric probability atlas of localized prostate cancer
A statistical volumetric model, showing the probability map of localized prostate cancer within the host anatomical structure, has been developed from 90 optically-imaged surgical specimens.
Spatial Neural Networks and their Functional Samples: Similarities and Differences
Models of neural networks have proven their utility in the development of learning algorithms in computer science and in the theoretical study of brain dynamics in computational neuroscience.
High Level Pattern Classification via Tourist Walks in Networks
Out of various high level perspectives that can be utilized to capture semantic meaning, we utilize the dynamical features that are generated from a tourist walker in a networked environment.
