Search Results for author:
Found 55 papers, 15 papers with code
Cooperative Control of Multi-Channel Linear Systems with Self-Organizing Private Agents
Cooperative behavior design for multi-agent systems with collective tasks is a critical issue to promote swarm intelligence.
FVP: Fourier Visual Prompting for Source-Free Unsupervised Domain Adaptation of Medical Image Segmentation
In FVP, the visual prompt is parameterized using only a small amount of low-frequency learnable parameters in the input frequency space, and is learned by minimizing the segmentation loss between the predicted segmentation of the prompted target image and reliable pseudo segmentation label of the target image under the frozen model.
Edge Deep Learning Model Protection via Neuron Authorization
With the development of deep learning processors and accelerators, deep learning models have been widely deployed on edge devices as part of the Internet of Things.
Efficient and Secure Federated Learning for Financial Applications
Experiments show that under different Non-IID experiment settings, our method can reduce the upload communication cost to about 2. 9% to 18. 9% of the conventional federated learning algorithm when the sparse rate is 0. 01.
Spectral Bayesian Uncertainty for Image Super-Resolution
In this paper, we propose to quantify spectral Bayesian uncertainty in image SR. To achieve this, a Dual-Domain Learning (DDL) framework is first proposed.
Biomedical image analysis competitions: The state of current participation practice
Of these, 84% were based on standard architectures.
BER: Balanced Error Rate For Speaker Diarization
DER is the primary metric to evaluate diarization performance while facing a dilemma: the errors in short utterances or segments tend to be overwhelmed by longer ones.
Consensus-based Frequency and Voltage Regulation for Fully Inverter-based Islanded Microgrids
The proposed method includes the active power sharing in voltage control to improve the reactive power sharing accuracy and thus generalizes some existing secondary frequency and voltage control methods.
Home-made blues: Residential crowding and mental health in Beijing, China
Although residential crowding has many well-being implications, its connection to mental health is yet to be widely examined.
The Roads One Must Walk Down: Commute and Depression for Beijing's Residents
As a vital aspect of individual's quality of life, mental health has been included as an important component of the U. N.
Normalized Feature Distillation for Semantic Segmentation
As a promising approach in model compression, knowledge distillation improves the performance of a compact model by transferring the knowledge from a cumbersome one.
ATC-Based Scenario Decomposition Algorithm for Optimal Power Flow of Distribution Networks Considering High Photovoltaic Penetration
This paper focuses on the analytical target cascading (ATC) based scenario decomposition method which applies to the stochastic OPF problem of distribution networks with high photovoltaic penetration.
Rethinking the Defense Against Free-rider Attack From the Perspective of Model Weight Evolving Frequency
To address these challenges, we reconsider the defense from a novel perspective, i. e., model weight evolving frequency. Empirically, we gain a novel insight that during the FL's training, the model weight evolving frequency of free-riders and that of benign clients are significantly different.
Anchor-Changing Regularized Natural Policy Gradient for Multi-Objective Reinforcement Learning
We study policy optimization for Markov decision processes (MDPs) with multiple reward value functions, which are to be jointly optimized according to given criteria such as proportional fairness (smooth concave scalarization), hard constraints (constrained MDP), and max-min trade-off.
Falconn++: A Locality-sensitive Filtering Approach for Approximate Nearest Neighbor Search
We present Falconn++, a novel locality-sensitive filtering approach for approximate nearest neighbor search on angular distance.
A Review of Landcover Classification with Very-High Resolution Remotely Sensed Optical Images-Analysis Unit,Model Scalability and Transferability
As an important application in remote sensing, landcover classification remains one of the most challenging tasks in very-high-resolution (VHR) image analysis.
Network resilience in the aging brain
Degeneration and adaptation are two competing sides of the same coin called resilience in the progressive processes of brain aging or diseases.
Neural network stochastic differential equation models with applications to financial data forecasting
In this article, we employ a collection of stochastic differential equations with drift and diffusion coefficients approximated by neural networks to predict the trend of chaotic time series which has big jump properties.
Policy Optimization for Constrained MDPs with Provable Fast Global Convergence
We propose a new algorithm called policy mirror descent-primal dual (PMD-PD) algorithm that can provably achieve a faster $\mathcal{O}(\log(T)/T)$ convergence rate for both the optimality gap and the constraint violation.
Fast Block Linear System Solver Using Q-Learning Schduling for Unified Dynamic Power System Simulations
The simulation on some large power systems shows that our solver is 2-6 times faster than KLU, which is the state-of-the-art sparse solver for circuit simulation problems.
Learning from Few Samples: Transformation-Invariant SVMs with Composition and Locality at Multiple Scales
Motivated by the problem of learning with small sample sizes, this paper shows how to incorporate into support-vector machines (SVMs) those properties that have made convolutional neural networks (CNNs) successful.
A Biologically Plausible Learning Rule for Perceptual Systems of organisms that Maximize Mutual Information
It is widely believed that the perceptual system of an organism is optimized for the properties of the environment to which it is exposed.
Chance Constrained Economic Dispatch Considering the Capability of Network Flexibility Against Renewable Uncertainties
In the proposed model, both power generations and line susceptances become variables to minimize the expected generation cost and guarantee a low probability of constraint violation in terms of generations and line flows under renewable uncertainties.
Augmented Synchronization of Power Systems
Here, we formulate the empirical wisdom by the concept of augmented synchronization and aim to bridge such a theory-practice gap.
Brain Age Estimation From MRI Using Cascade Networks with Ranking Loss
In this paper, a novel 3D convolutional network, called two-stage-age-network (TSAN), is proposed to estimate brain age from T1-weighted MRI data.
Learning Policies with Zero or Bounded Constraint Violation for Constrained MDPs
We show that when a strictly safe policy is known, then one can confine the system to zero constraint violation with arbitrarily high probability while keeping the reward regret of order $\tilde{\mathcal{O}}(\sqrt{K})$.
Sensing population distribution from satellite imagery via deep learning: model selection, neighboring effect, and systematic biases
The rapid development of remote sensing techniques provides rich, large-coverage, and high-temporal information of the ground, which can be coupled with the emerging deep learning approaches that enable latent features and hidden geographical patterns to be extracted.
Axi-Higgs Cosmology
If the electroweak Higgs vacuum expectation value $v$ in early universe is $\sim 1 \%$ higher than its present value $v_0=246$ GeV, the $^7$Li puzzle in BBN and the CMB/$\Lambda$CDM tension with late-universe measurements on Hubble parameter are mitigated.
High Energy Physics - Phenomenology Cosmology and Nongalactic Astrophysics High Energy Physics - Theory
Significant Inverse Magnetocaloric Effect induced by Quantum Criticality
Strong fluctuations in the low-$T$ quantum critical regime can give rise to a large thermal entropy change and thus significant cooling effect when approaching the QCP.
Strongly Correlated Electrons
Memory-Efficient Modeling and Slicing of Large-Scale Adaptive Lattice Structures
The presented methods have been validated by a series of case studies with large number (up to 100M) of struts to demonstrate its applicability to large-scale lattice structures.
Computational Geometry
A Benchmark for Voice-Face Cross-Modal Matching and Retrieval
In this paper, a baseline evaluation framework is proposed for voice-face matching and retrieval tasks.
Sentence Matching with Syntax- and Semantics-Aware BERT
Sentence matching aims to identify the special relationship between two sentences, and plays a key role in many natural language processing tasks.
The Tianlai Dish Pathfinder Array: design, operation and performance of a prototype transit radio interferometer
Combining all the baselines, we make maps around bright sources and show that the array behaves as expected.
Instrumentation and Methods for Astrophysics Cosmology and Nongalactic Astrophysics
MLPs to Find Extrema of Functionals
Multilayer perceptron (MLP) is a class of networks composed of multiple layers of perceptrons, and it is essentially a mathematical function.
BHN: A Brain-like Heterogeneous Network
The human brain works in an unsupervised way, and more than one brain region is essential for lighting up intelligence.
Voice-Face Cross-modal Matching and Retrieval: A Benchmark
It achieves state-of-the-art performance with various performance metrics on different tasks and with high test confidence on large scale datasets, which can be taken as a baseline for the follow-up research.
UER: An Open-Source Toolkit for Pre-training Models
Existing works, including ELMO and BERT, have revealed the importance of pre-training for NLP tasks.
Tiny but Accurate: A Pruned, Quantized and Optimized Memristor Crossbar Framework for Ultra Efficient DNN Implementation
To mitigate the challenges, the memristor crossbar array has emerged as an intrinsically suitable matrix computation and low-power acceleration framework for DNN applications.
Machine Vision Guided 3D Medical Image Compression for Efficient Transmission and Accurate Segmentation in the Clouds
In this paper we will use deep learning based medical image segmentation as a vehicle and demonstrate that interestingly, machine and human view the compression quality differently.
Classification using Ensemble Learning under Weighted Misclassification Loss
Binary classification rules based on covariates typically depend on simple loss functions such as zero-one misclassification.
Novelty Detection Meets Collider Physics
Complementary to supervised learning, it allows to analyze data model-independently.
Subword-level Composition Functions for Learning Word Embeddings
Subword-level information is crucial for capturing the meaning and morphology of words, especially for out-of-vocabulary entries.
Analogical Reasoning on Chinese Morphological and Semantic Relations
Analogical reasoning is effective in capturing linguistic regularities.
PT-Spike: A Precise-Time-Dependent Single Spike Neuromorphic Architecture with Efficient Supervised Learning
One of the most exciting advancements in AI over the last decade is the wide adoption of ANNs, such as DNN and CNN, in many real-world applications.
DeepN-JPEG: A Deep Neural Network Favorable JPEG-based Image Compression Framework
To reduce the data storage and transfer overhead in smart resource-limited Internet-of-Thing (IoT) systems, effective data compression is a "must-have" feature before transferring real-time produced dataset for training or classification.
Feature Distillation: DNN-Oriented JPEG Compression Against Adversarial Examples
Image compression-based approaches for defending against the adversarial-example attacks, which threaten the safety use of deep neural networks (DNN), have been investigated recently.
MT-Spike: A Multilayer Time-based Spiking Neuromorphic Architecture with Temporal Error Backpropagation
Modern deep learning enabled artificial neural networks, such as Deep Neural Network (DNN) and Convolutional Neural Network (CNN), have achieved a series of breaking records on a broad spectrum of recognition applications.
Security Analysis and Enhancement of Model Compressed Deep Learning Systems under Adversarial Attacks
In this work, we for the first time investigate the multi-factor adversarial attack problem in practical model optimized deep learning systems by jointly considering the DNN model-reshaping (e. g. HashNet based deep compression) and the input perturbations.
Ngram2vec: Learning Improved Word Representations from Ngram Co-occurrence Statistics
The existing word representation methods mostly limit their information source to word co-occurrence statistics.
Initializing Convolutional Filters with Semantic Features for Text Classification
Convolutional Neural Networks (CNNs) are widely used in NLP tasks.
Investigating Different Syntactic Context Types and Context Representations for Learning Word Embeddings
The number of word embedding models is growing every year.
Multiple-Kernel Based Vehicle Tracking Using 3D Deformable Model and Camera Self-Calibration
In this challenge, we propose a model-based vehicle localization method, which builds a kernel at each patch of the 3D deformable vehicle model and associates them with constraints in 3D space.
Weighted Neural Bag-of-n-grams Model: New Baselines for Text Classification
We train n-gram embeddings and use NB weighting to guide the neural models to focus on important words.
Residual Networks of Residual Networks: Multilevel Residual Networks
This paper proposes a novel residual-network architecture, Residual networks of Residual networks (RoR), to dig the optimization ability of residual networks.
Ranked #16 on
Image Classification
on SVHN
Learning Document Embeddings by Predicting N-grams for Sentiment Classification of Long Movie Reviews
Many document embeddings methods have been proposed to capture semantics, but they still can't outperform bag-of-ngram based methods on this task.
