“不v1不v2”是汉语中典型的双重否定结构形式之一, 它包括“不+助动词+不+v2”(不得不去)、“不+是+不v2”(不是不好)、述宾结构“不v1... 不v2”(不认为他不去)等多种双重否定结构, 情况复杂。本文以“不v1不v2”为例, 结合“元语否定”、“动词叙实性”、“否定焦点”等概念, 对“不v1不v2”进行了全面的考察, 制定了“不v1不v2”双重否定结构的识别策略。根据识别策略, 设计了双重否定自动识别程序, 并在此过程中补充了助动词表、非叙实动词表等词库。最终, 对28033句语料进行了识别, 识别正确率为97. 87%, 召回率约为93. 10%。
Boolean satisfiability (SAT) is one of the most well-known NP-complete problems and has been extensively studied.
Antimalware products are a key component in detecting malware attacks, and their engines typically execute unknown programs in a sandbox prior to running them on the native operating system.
Specifically, we design (1) Head-Tail Detector based on the multi-head self-attention mechanism and bi-affine classifier to detect boundary tokens, and (2) Token Interaction Tagger based on traditional sequence labeling approaches to characterize the internal token connection within the boundary.
We propose to pre-train a unified language model for both autoencoding and partially autoregressive language modeling tasks using a novel training procedure, referred to as a pseudo-masked language model (PMLM).
With the help of deep learning methods, the automatic identification or segmentation of nerves can be realized, assisting doctors in completing nerve block anesthesia accurately and efficiently.
CT-based bronchial tree analysis plays an important role in the computer-aided diagnosis for respiratory diseases, as it could provide structured information for clinicians.
To extend the reconstruction-based anomaly detection architecture to the localized anomalies, we propose a self-supervised learning approach through random masking and then restoring, named Self-Supervised Masking (SSM) for unsupervised anomaly detection and localization.
Current deep learning models for code summarization generally follow the principle in neural machine translation and adopt the encoder-decoder framework, where the encoder learns the semantic representations from source code and the decoder transforms the learnt representations into human-readable text that describes the functionality of code snippets.
In this paper, we present a novel approach for FGVC, which can simultaneously make use of partial yet sufficient discriminative information in environmental cues and also compress the redundant information in class-token with respect to the target.
We consider the flare prediction problem that distinguishes flare-imminent active regions that produce an M- or X-class flare in the future 24 hours, from quiet active regions that do not produce any flare within $\pm 24$ hours.
Both the primal and dual estimators are learned from data using supervised learning techniques, and the explicit sample size is provided, which enables us to guarantee the quality of each learned estimator in terms of feasibility and optimality.
Semantic segmentation with limited annotations, such as weakly supervised semantic segmentation (WSSS) and semi-supervised semantic segmentation (SSSS), is a challenging task that has attracted much attention recently.
Ranked #17 on Weakly-Supervised Semantic Segmentation on COCO 2014 val
We propose CodedVTR (Codebook-based Voxel TRansformer), which improves data efficiency and generalization ability for 3D sparse voxel transformers.
Federated Learning (FL) on knowledge graphs (KGs) has yet to be as well studied as other domains, such as computer vision and natural language processing.
Then the tensor was mapped to a matrix which was used to mix the one-hot encoded labels of the above image patches.
1 code implementation • 10 Feb 2022 • Benedek Rozemberczki, Charles Tapley Hoyt, Anna Gogleva, Piotr Grabowski, Klas Karis, Andrej Lamov, Andriy Nikolov, Sebastian Nilsson, Michael Ughetto, Yu Wang, Tyler Derr, Benjamin M Gyori
In this paper, we introduce ChemicalX, a PyTorch-based deep learning library designed for providing a range of state of the art models to solve the drug pair scoring task.
We conduct a comprehensive analysis of users' online game behaviors, which motivates the necessity of handling those three characteristics in the online game recommendation.
Machine learning algorithms typically assume that training and test examples are drawn from the same distribution.
Our work reveals a structured shortcoming of the existing mainstream self-supervised learning methods.
From this point, we present a particular paradigm of self-supervised learning tailored for domain adaptation, i. e., Transferrable Contrastive Learning (TCL), which links the SSL and the desired cross-domain transferability congruently.
Correspondingly, we also propose a novel "jury" mechanism, which is particularly effective in learning useful semantic feature commonalities among domains.
Ranked #15 on Domain Generalization on PACS
These scenarios indeed correspond to the vulnerabilities of the under-test driving policies, thus are meaningful for their further improvements.
The advent of machine learning models that surpass human decision-making ability in complex domains has initiated a movement towards building AI systems that interact with humans.
Graph Neural Networks (GNNs) have achieved unprecedented success in learning graph representations to identify categorical labels of graphs.
To address this issue, segmentation-based trackers have been proposed that employ per-pixel matching to improve the tracking performance of deformable objects effectively.
Our proposed Dynamic Preference Structure (DPS) framework consists of two stages: structure sampling and graph fusion.
In this paper, we propose a distributed formation and obstacle avoidance method based on multi-agent reinforcement learning (MARL).
We motivate our paradigm through a variational perspective, where the learning objective can be decomposed into two terms: task learning on the current task distribution, and curriculum update to a new task distribution.
Spinal degeneration plagues many elders, office workers, and even the younger generations.
In ATS, for the first time, we design a neural scheduler to decide which meta-training tasks to use next by predicting the probability being sampled for each candidate task, and train the scheduler to optimize the generalization capacity of the meta-model to unseen tasks.
Recent years have witnessed the significant success of applying graph neural networks (GNNs) in learning effective node representations for classification.
The same data are propagated through the graph structure to perform the same neural operation multiple times in GNNs, leading to redundant computation which accounts for 92. 4% of total operators.
In this paper, we extend the state-of-the-art single-agent visual navigation method, Active Neural SLAM (ANS), to the multi-agent setting by introducing a novel RL-based planning module, Multi-agent Spatial Planner (MSP). MSP leverages a transformer-based architecture, Spatial-TeamFormer, which effectively captures spatial relations and intra-agent interactions via hierarchical spatial self-attentions.
Although various flow models based on different transformations have been proposed, there still lacks a quantitative analysis of performance-cost trade-offs between different flows as well as a systematic way of constructing the best flow architecture.
Recent works on Binary Neural Networks (BNNs) have made promising progress in narrowing the accuracy gap of BNNs to their 32-bit counterparts, often based on specialized model designs using additional 32-bit components.
For the context block, we propose strip pooling module to capture anisotropic and long-range contextual information, which exists in abdominal scene.
To reduce the computational cost without sacrificing inferential accuracy, we propose Normalizing Flow with Adaptive Surrogate (NoFAS), an optimization strategy that alternatively updates the normalizing flow parameters and surrogate model parameters.
In the information explosion era, recommender systems (RSs) are widely studied and applied to discover user-preferred information.
Nevertheless, iterative propagation restricts the information of higher-layer neighborhoods to be transported through and fused with the lower-layer neighborhoods', which unavoidably results in feature smoothing between neighborhoods in different layers and can thus compromise the performance, especially on heterophily networks.
Ranked #10 on Node Classification on Cornell
In this paper, we construct a novel probabilistic graphical model that effectively incorporates the low rank promoting prior into the framework of contrastive learning, referred to as LORAC.
However, we identify two biases in existing datasets for XDTS: (1) a high proportion of context-independent questions and (2) a high proportion of easy SQL queries.
Due to the increasing concerns for data privacy, source-free unsupervised domain adaptation attracts more and more research attention, where only a trained source model is assumed to be available, while the labeled source data remain private.
Attempts of learning from hierarchical taxonomies in computer vision have been mostly focusing on image classification.
To learn the direct influence among output nodes in a graph, we propose the Explicit Pairwise Factorized Graph Neural Network (EPFGNN), which models the whole graph as a partially observed Markov Random Field.
no code implementations • 25 Jun 2021 • Yu Wang, Jinchao Li, Tristan Naumann, Chenyan Xiong, Hao Cheng, Robert Tinn, Cliff Wong, Naoto Usuyama, Richard Rogahn, Zhihong Shen, Yang Qin, Eric Horvitz, Paul N. Bennett, Jianfeng Gao, Hoifung Poon
A prominent case in point is the explosion of the biomedical literature on COVID-19, which swelled to hundreds of thousands of papers in a matter of months.
Recent works on Binary Neural Networks (BNNs) have made promising progress in narrowing the accuracy gap of BNNs to their 32-bit counterparts.
In this paper, we introduce a novel multi-step spoken language understanding system based on adversarial learning that can leverage the multiround user's feedback to update slot values.
In this paper, we present a coarse to fine question answering (CFQA) system based on reinforcement learning which can efficiently processes documents with different lengths by choosing appropriate actions.
We propose a new graphical model inference procedure, called SG-PALM, for learning conditional dependency structure of high-dimensional tensor-variate data.
A noisy negative example which is uninteracted because of unawareness of the user could also denote potential positive user preference.
Next generation beyond 5G networks are expected to provide both Terabits per second data rate communication services and centimeter-level accuracy localization services in an efficient, seamless and cost-effective manner.
The directions of weights, and the gradients, can be divided into domain-specific and domain-invariant parts, and the goal of domain adaptation is to concentrate on the domain-invariant direction while eliminating the disturbance from domain-specific one.
Despite their success, however, low/high spatial resolution pairs are usually difficult to obtain in satellites with a high temporal resolution, making such approaches in SR impractical to use.
We firstly pre-train a transformer with sequences in a reverse direction to predict prior items.
Membership inference attacks (MIAs) infer whether a specific data record is used for target model training.
We then perform a systematic study on existing long-tailed recognition methods in conjunction with the adversarial training framework.
This paper describes the ExKaldi-RT online automatic speech recognition (ASR) toolkit that is implemented based on the Kaldi ASR toolkit and Python language.
It provides high scalability because the paths within an EIO network exponentially increase with the network depth.
We study the problem of learning safe control policies that are also effective; i. e., maximizing the probability of satisfying a linear temporal logic (LTL) specification of a task, and the discounted reward capturing the (classic) control performance.
In this work, we propose FedCor -- an FL framework built on a correlation-based client selection strategy, to boost the convergence rate of FL.
Most online multi-object trackers perform object detection stand-alone in a neural net without any input from tracking.
Ranked #1 on Online Multi-Object Tracking on MOT16
Aspect sentiment triplet extraction (ASTE), which aims to identify aspects from review sentences along with their corresponding opinion expressions and sentiments, is an emerging task in fine-grained opinion mining.
This work focuses on the use of deep learning for vulnerability analysis of cyber-physical systems (CPS).
We propose a simple, general and effective technique, Reward Randomization for discovering diverse strategic policies in complex multi-agent games.
Proximal Policy Optimization (PPO) is a popular on-policy reinforcement learning algorithm but is significantly less utilized than off-policy learning algorithms in multi-agent settings.
1 code implementation • 1 Mar 2021 • Yukuo Cen, Zhenyu Hou, Yan Wang, Qibin Chen, Yizhen Luo, Zhongming Yu, Hengrui Zhang, Xingcheng Yao, Aohan Zeng, Shiguang Guo, Yuxiao Dong, Yang Yang, Peng Zhang, Guohao Dai, Yu Wang, Chang Zhou, Hongxia Yang, Jie Tang
Deep learning on graphs has attracted tremendous attention from the graph learning community in recent years.
Iterative Random Forests (iRF) use a tree ensemble from iteratively modified RF to obtain predictive and stable non-linear or Boolean interactions of features.
Statistics Theory Statistics Theory
Recently a class of quantum systems exhibiting weak ergodicity breaking has attracted much attention.
Disordered Systems and Neural Networks Statistical Mechanics
By deriving distinct rewards and discount factors from the acceptance condition of the DPA, we reduce the maximization of the worst-case probability of satisfying the LTL specification into the maximization of a discounted reward objective in the product game; this allows for the use of model-free RL algorithms to learn an optimal controller strategy.
Compute-in-memory (CiM) is a promising approach to alleviating the memory wall problem for domain-specific applications.
1 code implementation • 10 Jan 2021 • Guyue Huang, Jingbo Hu, Yifan He, Jialong Liu, Mingyuan Ma, Zhaoyang Shen, Juejian Wu, Yuanfan Xu, Hengrui Zhang, Kai Zhong, Xuefei Ning, Yuzhe ma, HaoYu Yang, Bei Yu, Huazhong Yang, Yu Wang
With the down-scaling of CMOS technology, the design complexity of very large-scale integrated (VLSI) is increasing.
Through this dynamic precision framework, we can reduce the bit-width of convolution, which is the most computational cost, while keeping the training process close to the full precision floating-point training.
We benchmark commonly used multi-agent deep reinforcement learning (MARL) algorithms on a variety of cooperative multi-agent games.
In this paper, considering scenarios with capacity budget, we aim to discover adversarially robust architecture at targeted capacities.
The early detection of CKD faces challenges of insufficient medical histories of positive patients and complicated risk factors.
(2) Since the target data arrive online, the agent should also maintain competence on previous target domains, i. e. to adapt without forgetting.
Neural Architecture Search (NAS) has received extensive attention due to its capability to discover neural network architectures in an automated manner.
We also design the micro-level search space to strengthen the information flow for BNN.
Learning depth and ego-motion from unlabeled videos via self-supervision from epipolar projection can improve the robustness and accuracy of the 3D perception and localization of vision-based robots.
This paper presents the design of a tune-free (human-out-of-the-loop parameter tuning) control framework, aiming at accelerating large scale autonomous driving system deployed on various vehicles and driving environments.
However, most of them fail to take into account the overall facial profile and fine texture details simultaneously, resulting in reduced naturalness and fidelity of the reconstructed face, and further impairing the performance of downstream tasks (e. g., face detection, facial recognition).
Task-agnostic forms of data augmentation have proven widely effective in computer vision, even on pretrained models.
A major challenge in NAS is to conduct a fast and accurate evaluation of neural architectures.
On the other hand, FPGA-based robotic accelerators are becoming increasingly competitive alternatives, especially in latency-critical and power-limited scenarios.
no code implementations • 11 Sep 2020 • Mark Cartwright, Jason Cramer, Ana Elisa Mendez Mendez, Yu Wang, Ho-Hsiang Wu, Vincent Lostanlen, Magdalena Fuentes, Graham Dove, Charlie Mydlarz, Justin Salamon, Oded Nov, Juan Pablo Bello
In this article, we describe our data collection procedure and propose evaluation metrics for multilabel classification of urban sound tags.
The evaluation information is backpropagated and forces the classification stream to improve its awareness of visual attention, which helps classification.
Ranked #17 on Fine-Grained Image Classification on Stanford Cars
The existing localization systems for indoor applications basically rely on wireless signal.
Conducting efficient performance estimations of neural architectures is a major challenge in neural architecture search (NAS).
In system analysis, conformance indicates that two systems simultaneously satisfy the same set of specifications of interest; thus, the results from analyzing one system automatically transfer to the other, or one system can safely replace the other in practice.
In this paper, we tackle the issue of physical adversarial examples for object detectors in the wild.
We present a new loss function called Distribution-Balanced Loss for the multi-label recognition problems that exhibit long-tailed class distributions.
1 code implementation • 13 Jul 2020 • Ahmed Elnaggar, Michael Heinzinger, Christian Dallago, Ghalia Rihawi, Yu Wang, Llion Jones, Tom Gibbs, Tamas Feher, Christoph Angerer, Martin Steinegger, Debsindhu Bhowmik, Burkhard Rost
Here, we trained two auto-regressive models (Transformer-XL, XLNet) and four auto-encoder models (BERT, Albert, Electra, T5) on data from UniRef and BFD containing up to 393 billion amino acids.
Ranked #1 on Protein Secondary Structure Prediction on CB513
Some works in the optimization of deep neural networks have shown that a better arrangement of training data can make the classifier converge faster and perform better.
GE-SpMM performs SpMM-like operation on sparse matrices represented in the most common Compressed Sparse Row (CSR) format, so it can be embedded in GNN frameworks with no preprocessing overheads and support general GNN algorithms.
Distributed, Parallel, and Cluster Computing
The COVID-19 pandemic has severely affected people's daily lives and caused tremendous economic loss worldwide.
The opinion entity extraction unit and the relation detection unit are developed as two channels to extract opinion entities and relations simultaneously.
A practical autonomous driving system urges the need to reliably and accurately detect vehicles and persons.
We proposed a one-stage, anchor-free and NMS-free 3D point cloud object detector AFDet, using object key-points to encode the 3D attributes, and to learn an end-to-end point cloud object detection without the need of hand-engineering or learning the anchors.
This technical report presents the online and real-time 2D and 3D multi-object tracking (MOT) algorithms that reached the 1st places on both Waymo Open Dataset 2D tracking and 3D tracking challenges.
High-efficiency point cloud 3D object detection operated on embedded systems is important for many robotics applications including autonomous driving.
Monotone systems, originating from real-world (e. g., biological or chemical) applications, are a class of dynamical systems that preserves a partial order of system states over time.
To this end, we devise a general loss function to cover most region-based object detectors with various sampling strategies, and then based on it we propose a unified sample weighting network to predict a sample's task weights.
For training a variety of models on CIFAR-10, using 1-bit mantissa and 2-bit exponent is adequate to keep the accuracy loss within $1\%$.
Compared with the existing AKI predictors, the predictor in this work greatly improves the precision of early prediction of AKI by using the Convolutional Neural Network architecture and a more concise input vector.
Multi-hop knowledge based question answering (KBQA) is a complex task for natural language understanding.
We have also created a neural bug detector based on GINN to catch null pointer deference bugs in Java code.
1 code implementation • 16 May 2020 • Nick Altieri, Rebecca L. Barter, James Duncan, Raaz Dwivedi, Karl Kumbier, Xiao Li, Robert Netzorg, Briton Park, Chandan Singh, Yan Shuo Tan, Tiffany Tang, Yu Wang, Chao Zhang, Bin Yu
We use this data to develop predictions and corresponding prediction intervals for the short-term trajectory of COVID-19 cumulative death counts at the county-level in the United States up to two weeks ahead.
Unlike existing work in deep neural network (DNN) graphs optimization for inference performance, we explore DNN graph optimization for energy awareness and savings for power- and resource-constrained machine learning devices.
More importantly, we discuss four kinds of basic approaches, including statistical machine translation based approach, neural machine translation based approach, classification based approach and language model based approach, six commonly applied performance boosting techniques for GEC systems and two data augmentation methods.
To model the substantive difference of tweets with controversial terms and those with non-controversial terms, we apply topic modeling and LIWC-based sentiment analysis.
Recently, the pandemic of the novel Coronavirus Disease-2019 (COVID-19) has presented governments with ultimate challenges.
In natural language processing (NLP), pre-training large neural language models such as BERT have demonstrated impressive gain in generalization for a variety of tasks, with further improvement from adversarial fine-tuning.
Ranked #3 on Natural Language Inference on ANLI test (using extra training data)
Simulation results verify the efficiency of the proposed algorithms and reveal the impacts of CSI uncertainties on ST's minimum transmit power and feasibility rate of the optimization problems.
In budgeted pruning, how to distribute the resources across layers (i. e., sparsity allocation) is the key problem.
Experimental results on various search spaces confirm GATES's effectiveness in improving the performance predictor.
Using the two examples: sequential probability ratio test and sequential empirical risk minimization, we show that the number of steps such algorithms execute before termination can jeopardize the differential privacy of the input data in a similar fashion as their outputs, and it is impossible to use the usual Laplace mechanism to achieve standard differentially private in these examples.
Probabilistic Computation Tree Logic (PCTL) is frequently used to formally specify control objectives such as probabilistic reachability and safety.
Currently, the majority of FPGA-based DNN accelerators in the cloud run in a time-division multiplexing way for multiple users sharing a single FPGA, and require re-compilation with $\sim$100 s overhead.
By inspecting the discovered architectures, we find that the operation primitives, the weight quantization range, the capacity of the model, and the connection pattern have influences on the fault resilience capability of NN models.
We propose to pre-train a unified language model for both autoencoding and partially autoregressive language modeling tasks using a novel training procedure, referred to as a pseudo-masked language model (PMLM).
Ranked #3 on Question Generation on SQuAD1.1 (using extra training data)
We present MT-DNN, an open-source natural language understanding (NLU) toolkit that makes it easy for researchers and developers to train customized deep learning models.
Then, we apply these pre-training models to a NER task by fine-tuning, and compare the effects of the different model architecture and pre-training tasks on the NER task.
Previous database systems extended their SQL dialect to support ML.
Evaluations based on the 65nm technology demonstrate that the proposed architecture nearly reaches the theoretical minimum communication in a three-level memory hierarchy and it is computation dominant.
Distributed, Parallel, and Cluster Computing Hardware Architecture
Some suggestions towards congestion mitigation for future mMP studies are proposed: i) enrich data collection to facilitate the congestion learning, ii) incorporate non-imitation learning methods to combine traffic efficiency into a safety-oriented technical route, and iii) integrate domain knowledge from the traditional car following (CF) theory to improve the string stability of mMP.
We present a reinforcement learning (RL) framework to synthesize a control policy from a given linear temporal logic (LTL) specification in an unknown stochastic environment that can be modeled as a Markov Decision Process (MDP).
With the development of artificial intelligence algorithms like deep learning models and the successful applications in many different fields, further similar trails of deep learning technology have been made in cyber security area.
In a cross-project prediction task, three neural bug detectors we instantiate from NeurSA are effective in catching null pointer dereference, array index out of bound and class cast bugs in unseen code.
Based on the original definition of MDI by Breiman et al. for a single tree, we derive a tight non-asymptotic bound on the expected bias of MDI importance of noisy features, showing that deep trees have higher (expected) feature selection bias than shallow ones.
The whole network has nearly symmetric architecture, which is mainly composed of a series of factorized convolution unit (FCU) and its parallel counterparts (PFCU).
Ranked #25 on Real-Time Semantic Segmentation on Cityscapes test
A novel variational inference based resampling framework is proposed to evaluate the robustness and generalization capability of deep learning models with respect to distribution shift.
3 code implementations • 14 May 2019 • Weitian Li, Haiguang Xu, Zhixian Ma, Dan Hu, Zhenghao Zhu, Chenxi Shan, Jingying Wang, Junhua Gu, Dongchao Zheng, Xiaoli Lian, Qian Zheng, Yu Wang, Jie Zhu, Xiang-Ping Wu
The overwhelming foreground contamination is one of the primary impediments to probing the EoR through measuring the redshifted 21 cm signal.
Cosmology and Nongalactic Astrophysics
This paper presents a new Unified pre-trained Language Model (UniLM) that can be fine-tuned for both natural language understanding and generation tasks.
Ranked #2 on Generative Question Answering on CoQA (using extra training data)
LEDNet: A Lightweight Encoder-Decoder Network for Real-time Semantic Segmentation
Ranked #26 on Real-Time Semantic Segmentation on Cityscapes test
Specifically, we present Transferrable Prototypical Networks (TPN) for adaptation such that the prototypes for each class in source and target domains are close in the embedding space and the score distributions predicted by prototypes separately on source and target data are similar.
Measurement and estimation of parameters are essential for science and engineering, where one of the main quests is to find systematic schemes that can achieve high precision.
Quantum Physics Mesoscale and Nanoscale Physics
First, we obtain a necessary and sufficient norm condition for the reference dictionary $D^*$ to be a sharp local minimum of the expected $\ell_1$ objective function.
On the Xilinx ZU2 @330 MHz and ZU9 @330 MHz, we achieve equivalently state-of-the-art performance on our benchmarks by na\"ive implementations without optimizations, and the throughput is further improved up to 1. 26x by leveraging heterogeneous optimizations in DNNVM.
In this paper, a new deep reinforcement learning based augmented general sequence tagging system is proposed.
The most effective algorithms are based on the structures of sequence to sequence models (or "encoder-decoder" models), and generate the intents and semantic tags either using separate models or a joint model.
Ranked #1 on Slot Filling on ATIS
These errors are not accounted for by the standard confidence estimation schemes and are hard to rectify in the upstream and downstream processing.
It is common that entity mentions can contain other mentions recursively.
Ranked #6 on Nested Named Entity Recognition on NNE
The results show that our approach leverages such simple user information to outperform state-of-the-art approaches by 0. 25% for intent detection and 0. 31% for slot filling using standard training data.
In this paper, a new deep reinforcement learning based augmented general tagging system is proposed.
This proposal introduces a Dialogue Challenge for building end-to-end task-completion dialogue systems, with the goal of encouraging the dialogue research community to collaborate and benchmark on standard datasets and unified experimental environment.
Moreover, we also propose HiTM-VAE, where the document-specific topic distributions are generated in a hierarchical manner.
The estimation of crowd count in images has a wide range of applications such as video surveillance, traffic monitoring, public safety and urban planning.
So, in this paper, we propose a hardware-software collaborative attack framework to inject hidden neural network Trojans, which works as a back-door without requiring manipulating input images and is flexible for different scenarios.
We examine in this paper the problem of identifying the camera model or type that was used to take an image and that can be spoofed.
With the popularity of deep learning (DL), artificial intelligence (AI) has been applied in many areas of human life.
As the combination approaches become more complicated the difference between the phonetic and graphemic systems further decreases.
On the other hand, different with the other BNP topic models, the inference of iTM-VAE is modeled by neural networks, which has rich representation capacity and can be computed in a simple feed-forward manner.
Various FPGA based accelerator designs have been proposed with software and hardware optimization techniques to achieve high speed and energy efficiency.
Large-scale distributed training requires significant communication bandwidth for gradient exchange that limits the scalability of multi-node training, and requires expensive high-bandwidth network infrastructure.
The situation gets even worse with distributed training on mobile devices (federated learning), which suffers from higher latency, lower throughput, and intermittent poor connections.