Search Results for author:
Found 50 papers, 13 papers with code
Boosting Deep Neural Network Efficiency with Dual-Module Inference
Using Deep Neural Networks (DNNs) in machine learning tasks is promising in delivering high-quality results but challenging to meet stringent latency requirements and energy constraints because of the memory-bound and the compute-bound execution pattern of DNNs.
Attention Spiking Neural Networks
On ImageNet-1K, we achieve top-1 accuracy of 75. 92% and 77. 08% on single/4-step Res-SNN-104, which are state-of-the-art results in SNNs.
Attention-wise masked graph contrastive learning for predicting molecular property
We developed a novel molecular graph augmentation strategy, referred to as attention-wise graph mask, to generate challenging positive sample for contrastive learning.
Contrastive learning-based computational histopathology predict differential expression of cancer driver genes
We leveraged contrastive learning on large-scale unannotated WSIs to derive slide-level histopathological feature in latent space, and then transfer it to tumor diagnosis and prediction of differentially expressed cancer driver genes.
Toward Robust Spiking Neural Network Against Adversarial Perturbation
To the best of our knowledge, this is the first analysis on robust training of SNNs.
Spiking Neural Network Integrated Circuits: A Review of Trends and Future Directions
In this paper, we reviewed Spiking neural network (SNN) integrated circuit designs and analyzed the trends among mixed-signal cores, fully digital cores and large-scale, multi-core designs.
A Deep Learning Approach to Predicting Ventilator Parameters for Mechanically Ventilated Septic Patients
We develop a deep learning approach to predicting a set of ventilator parameters for a mechanically ventilated septic patient using a long and short term memory (LSTM) recurrent neural network (RNN) model.
Survey on Graph Neural Network Acceleration: An Algorithmic Perspective
Next, we provide comparisons from aspects of the efficiency and characteristics of these methods.
Advancing Spiking Neural Networks towards Deep Residual Learning
Despite the rapid progress of neuromorphic computing, inadequate capacity and insufficient representation power of spiking neural networks (SNNs) severely restrict their application scope in practice.
Advancing Deep Residual Learning by Solving the Crux of Degradation in Spiking Neural Networks
In this paper, we identify the crux and then propose a novel residual block for SNNs, which is able to significantly extend the depth of directly trained SNNs, e. g., up to 482 layers on CIFAR-10 and 104 layers on ImageNet, without observing any slight degradation problem.
ES-ImageNet: A Million Event-Stream Classification Dataset for Spiking Neural Networks
With event-driven algorithms, especially the spiking neural networks (SNNs), achieving continuous improvement in neuromorphic vision processing, a more challenging event-stream-dataset is urgently needed.
Graph2MDA: a multi-modal variational graph embedding model for predicting microbe-drug associations
We evaluated our method on three independent datasets and the experimental results showed that our proposed method outperformed six existing state-of-the-art methods.
Dynamic Control for Random Access in Deadline-Constrained Broadcasting
To overcome the infeasibility in obtaining an optimal or near-optimal scheme from the POMDP framework, we investigate the behaviors of the optimal scheme for two extreme cases in the MDP framework, and leverage intuition gained from these behaviors to propose a heuristic scheme for the realistic environment with TDR close to the maximum achievable TDR in the idealized environment.
H2Learn: High-Efficiency Learning Accelerator for High-Accuracy Spiking Neural Networks
Although spiking neural networks (SNNs) take benefits from the bio-plausible neural modeling, the low accuracy under the common local synaptic plasticity learning rules limits their application in many practical tasks.
Exploiting Spiking Dynamics with Spatial-temporal Feature Normalization in Graph Learning
Biological spiking neurons with intrinsic dynamics underlie the powerful representation and learning capabilities of the brain for processing multimodal information in complex environments.
Towards Efficient Full 8-bit Integer DNN Online Training on Resource-limited Devices without Batch Normalization
In summary, the EOQ framework is specially designed for reducing the high cost of convolution and BN in network training, demonstrating a broad application prospect of online training in resource-limited devices.
Sampling methods for efficient training of graph convolutional networks: A survey
Graph Convolutional Networks (GCNs) have received significant attention from various research fields due to the excellent performance in learning graph representations.
Redefining Self-Normalization Property
Moreover, analysis on the activation's mean in the forward pass reveals that the self-normalization property gets weaker with larger fan-in of each layer, which explains the performance degradation on large benchmarks like ImageNet.
Training and Inference for Integer-Based Semantic Segmentation Network
However, neural network quantization can be used to reduce computation load while maintaining comparable accuracy and original network structure.
Going Deeper With Directly-Trained Larger Spiking Neural Networks
To this end, we propose a threshold-dependent batch normalization (tdBN) method based on the emerging spatio-temporal backpropagation, termed "STBP-tdBN", enabling direct training of a very deep SNN and the efficient implementation of its inference on neuromorphic hardware.
Rubik: A Hierarchical Architecture for Efficient Graph Learning
Graph convolutional network (GCN) emerges as a promising direction to learn the inductive representation in graph data commonly used in widespread applications, such as E-commerce, social networks, and knowledge graphs.
Hardware Architecture
Kronecker CP Decomposition with Fast Multiplication for Compressing RNNs
Recurrent neural networks (RNNs) are powerful in the tasks oriented to sequential data, such as natural language processing and video recognition.
Hybrid Tensor Decomposition in Neural Network Compression
We further theoretically and experimentally discover that the HT format has better performance on compressing weight matrices, while the TT format is more suited for compressing convolutional kernels.
GNNAdvisor: An Adaptive and Efficient Runtime System for GNN Acceleration on GPUs
As the emerging trend of graph-based deep learning, Graph Neural Networks (GNNs) excel for their capability to generate high-quality node feature vectors (embeddings).
Distributed, Parallel, and Cluster Computing
Brain-inspired global-local learning incorporated with neuromorphic computing
We demonstrate the advantages of this model in multiple different tasks, including few-shot learning, continual learning, and fault-tolerance learning in neuromorphic vision sensors.
Comparing SNNs and RNNs on Neuromorphic Vision Datasets: Similarities and Differences
Neuromorphic data, recording frameless spike events, have attracted considerable attention for the spatiotemporal information components and the event-driven processing fashion.
Ranked #4 on
Gesture Recognition
on DVS128 Gesture
HyGCN: A GCN Accelerator with Hybrid Architecture
In this work, we first characterize the hybrid execution patterns of GCNs on Intel Xeon CPU.
Distributed, Parallel, and Cluster Computing
Exploring Adversarial Attack in Spiking Neural Networks with Spike-Compatible Gradient
Recently, backpropagation through time inspired learning algorithms are widely introduced into SNNs to improve the performance, which brings the possibility to attack the models accurately given Spatio-temporal gradient maps.
A Comprehensive and Modularized Statistical Framework for Gradient Norm Equality in Deep Neural Networks
Powered by our metric and framework, we analyze extensive initialization, normalization, and network structures.
Transfer Learning in General Lensless Imaging through Scattering Media
In summary, this work provides a new solution for lensless imaging through scattering media using transfer learning in DNNs.
Compressing 3DCNNs Based on Tensor Train Decomposition
However, due to the higher dimension of convolutional kernels, the space complexity of 3DCNNs is generally larger than that of traditional two dimensional convolutional neural networks (2DCNNs).
Comprehensive SNN Compression Using ADMM Optimization and Activity Regularization
As well known, the huge memory and compute costs of both artificial neural networks (ANNs) and spiking neural networks (SNNs) greatly hinder their deployment on edge devices with high efficiency.
Dual-module Inference for Efficient Recurrent Neural Networks
Using Recurrent Neural Networks (RNNs) in sequence modeling tasks is promising in delivering high-quality results but challenging to meet stringent latency requirements because of the memory-bound execution pattern of RNNs.
DashNet: A Hybrid Artificial and Spiking Neural Network for High-speed Object Tracking
To the best of our knowledge, DashNet is the first framework that can integrate and process ANNs and SNNs in a hybrid paradigm, which provides a novel solution to achieve both effectiveness and efficiency for high-speed object tracking.
Training High-Performance and Large-Scale Deep Neural Networks with Full 8-bit Integers
In this way, all the operations in the training and inference can be bit-wise operations, pushing towards faster processing speed, decreased memory cost, and higher energy efficiency.
AccD: A Compiler-based Framework for Accelerating Distance-related Algorithms on CPU-FPGA Platforms
As a promising solution to boost the performance of distance-related algorithms (e. g., K-means and KNN), FPGA-based acceleration attracts lots of attention, but also comes with numerous challenges.
Distributed, Parallel, and Cluster Computing Programming Languages
Effective and Efficient Batch Normalization Using Few Uncorrelated Data for Statistics' Estimation
We identify that the effectiveness expects less data correlation while the efficiency expects regular execution pattern.
Neural Network Model Extraction Attacks in Edge Devices by Hearing Architectural Hints
As neural networks continue their reach into nearly every aspect of software operations, the details of those networks become an increasingly sensitive subject.
Cryptography and Security Hardware Architecture
TETRIS: TilE-matching the TRemendous Irregular Sparsity
Increasing the sparsity granularity can lead to better hardware utilization, but it will compromise the sparsity for maintaining accuracy.
HitNet: Hybrid Ternary Recurrent Neural Network
For example, we improve the perplexity per word (PPW) of a ternary LSTM on Penn Tree Bank (PTB) corpus from 126 (the state-of-the-art result to the best of our knowledge) to 110. 3 with a full precision model in 97. 2, and a ternary GRU from 142 to 113. 5 with a full precision model in 102. 7.
Batch Normalization Sampling
In this paper, we propose alleviating this problem through sampling only a small fraction of data for normalization at each iteration.
Dynamic Sparse Graph for Efficient Deep Learning
We propose to execute deep neural networks (DNNs) with dynamic and sparse graph (DSG) structure for compressive memory and accelerative execution during both training and inference.
Direct Training for Spiking Neural Networks: Faster, Larger, Better
Spiking neural networks (SNNs) that enables energy efficient implementation on emerging neuromorphic hardware are gaining more attention.
Crossbar-aware neural network pruning
Crossbar architecture based devices have been widely adopted in neural network accelerators by taking advantage of the high efficiency on vector-matrix multiplication (VMM) operations.
L1-Norm Batch Normalization for Efficient Training of Deep Neural Networks
Batch Normalization (BN) has been proven to be quite effective at accelerating and improving the training of deep neural networks (DNNs).
Satellite-relayed intercontinental quantum network
This was on the one hand the transmission of images in a one-time pad configuration from China to Austria as well as from Austria to China.
Quantum Physics
Device-to-Device Load Balancing for Cellular Networks
The idea is to shift traffic from a congested cell to its adjacent under-utilized cells by leveraging inter-cell D2D communication, so that the traffic can be served without using extra spectrum, effectively improving the spectrum temporal efficiency.
Networking and Internet Architecture
Spatio-Temporal Backpropagation for Training High-performance Spiking Neural Networks
By simultaneously considering the layer-by-layer spatial domain (SD) and the timing-dependent temporal domain (TD) in the training phase, as well as an approximated derivative for the spike activity, we propose a spatio-temporal backpropagation (STBP) training framework without using any complicated technology.
GXNOR-Net: Training deep neural networks with ternary weights and activations without full-precision memory under a unified discretization framework
Through this way, we build a unified framework that subsumes the binary or ternary networks as its special cases, and under which a heuristic algorithm is provided at the website https://github. com/AcrossV/Gated-XNOR.
Image Set Querying Based Localization
Conventional single image based localization methods usually fail to localize a querying image when there exist large variations between the querying image and the pre-built scene.
