research
∙
09/01/2023
Structure and Gradient Dynamics Near Global Minima of Two-layer Neural Networks
Under mild assumptions, we investigate the structure of loss landscape o...
share
research
∙
07/18/2023
Optimistic Estimate Uncovers the Potential of Nonlinear Models
We propose an optimistic estimate to evaluate the best possible fitting ...
research
∙
06/08/2023
A Class of Smoothing Modulus-Based Iterative Method for Solving Implicit Complementarity Problems
In this paper, a class of smoothing modulus-based iterative method was p...
research
∙
05/25/2023
Stochastic Modified Equations and Dynamics of Dropout Algorithm
Dropout is a widely utilized regularization technique in the training of...
research
∙
05/11/2023
Numerical Stability for Differential Equations with Memory
In this work, we systematically investigate linear multi-step methods fo...
research
∙
05/09/2023
DeepFire2: A Convolutional Spiking Neural Network Accelerator on FPGAs
Brain-inspired spiking neural networks (SNNs) replace the multiply-accum...
research
∙
04/23/2023
Hierarchical Weight Averaging for Deep Neural Networks
Despite the simplicity, stochastic gradient descent (SGD)-like algorithm...
research
∙
03/12/2023
Phase Diagram of Initial Condensation for Two-layer Neural Networks
The phenomenon of distinct behaviors exhibited by neural networks under ...
research
∙
01/01/2023
Optimization of Image Transmission in a Cooperative Semantic Communication Networks
In this paper, a semantic communication framework for image transmission...
research
∙
11/21/2022
Linear Stability Hypothesis and Rank Stratification for Nonlinear Models
Models with nonlinear architectures/parameterizations such as deep neura...
research
∙
11/10/2022
Desire Backpropagation: A Lightweight Training Algorithm for Multi-Layer Spiking Neural Networks based on Spike-Timing-Dependent Plasticity
Spiking neural networks (SNN) are a viable alternative to conventional a...
research
∙
10/12/2022
Statistical Modeling of Soft Error Influence on Neural Networks
Soft errors in large VLSI circuits pose dramatic influence on computing-...
research
∙
10/11/2022
Image Segmentation Semantic Communication over Internet of Vehicles
In this paper, the problem of semantic-based efficient image transmissio...
research
∙
08/17/2022
Performance Optimization for Semantic Communications: An Attention-based Reinforcement Learning Approach
In this paper, a semantic communication framework is proposed for textua...
research
∙
06/06/2022
A Resource-efficient Spiking Neural Network Accelerator Supporting Emerging Neural Encoding
Spiking neural networks (SNNs) recently gained momentum due to their low...
research
∙
05/26/2022
Embedding Principle in Depth for the Loss Landscape Analysis of Deep Neural Networks
Unraveling the general structure underlying the loss landscapes of deep ...
research
∙
05/25/2022
An Experimental Comparison Between Temporal Difference and Residual Gradient with Neural Network Approximation
Gradient descent or its variants are popular in training neural networks...
research
∙
05/24/2022
Empirical Phase Diagram for Three-layer Neural Networks with Infinite Width
Substantial work indicates that the dynamics of neural networks (NNs) is...
research
∙
02/17/2022
Winograd Convolution: A Perspective from Fault Tolerance
Winograd convolution is originally proposed to reduce the computing over...
research
∙
01/28/2022
Limitation of characterizing implicit regularization by data-independent functions
In recent years, understanding the implicit regularization of neural net...
research
∙
01/19/2022
Overview frequency principle/spectral bias in deep learning
Understanding deep learning is increasingly emergent as it penetrates mo...
research
∙
12/01/2021
Optimizing for In-memory Deep Learning with Emerging Memory Technology
In-memory deep learning computes neural network models where they are st...
research
∙
11/30/2021
Embedding Principle: a hierarchical structure of loss landscape of deep neural networks
We prove a general Embedding Principle of loss landscape of deep neural ...
research
∙
11/19/2021
E3NE: An End-to-End Framework for Accelerating Spiking Neural Networks with Emerging Neural Encoding on FPGAs
Compiler frameworks are crucial for the widespread use of FPGA-based dee...
research
∙
07/08/2021
MOD-Net: A Machine Learning Approach via Model-Operator-Data Network for Solving PDEs
In this paper, we propose a model-operator-data network (MOD-Net) for so...
research
∙
06/29/2021
Privacy Budget Scheduling
Machine learning (ML) models trained on personal data have been shown to...
research
∙
05/30/2021
Embedding Principle of Loss Landscape of Deep Neural Networks
Understanding the structure of loss landscape of deep neural networks (D...
research
∙
05/25/2021
DTNN: Energy-efficient Inference with Dendrite Tree Inspired Neural Networks for Edge Vision Applications
Deep neural networks (DNN) have achieved remarkable success in computer ...
research
∙
05/25/2021
Towards Understanding the Condensation of Two-layer Neural Networks at Initial Training
It is important to study what implicit regularization is imposed on the ...
research
∙
05/25/2021
An Upper Limit of Decaying Rate with Respect to Frequency in Deep Neural Network
Deep neural network (DNN) usually learns the target function from low to...
research
∙
05/14/2021
Efficient Spiking Neural Networks with Radix Encoding
Spiking neural networks (SNNs) have advantages in latency and energy eff...
research
∙
03/30/2021
Nonlinear Weighted Directed Acyclic Graph and A Priori Estimates for Neural Networks
In an attempt to better understand structural benefits and generalizatio...
research
∙
03/26/2021
RCT: Resource Constrained Training for Edge AI
Neural networks training on edge terminals is essential for edge AI comp...
research
∙
03/19/2021
QROSS: QUBO Relaxation Parameter Optimisation via Learning Solver Surrogates
An increasingly popular method for solving a constrained combinatorial o...
research
∙
03/17/2021
Convergence from Atomistic Model to Peierls-Nabarro Model for Dislocations in Bilayer System with Complex Lattice
In this paper, we prove the convergence from the atomistic model to the ...
research
∙
01/30/2021
Linear Frequency Principle Model to Understand the Absence of Overfitting in Neural Networks
Why heavily parameterized neural networks (NNs) do not overfit the data ...
research
∙
01/29/2021
Meta-Reinforcement Learning for Reliable Communication in THz/VLC Wireless VR Networks
In this paper, the problem of enhancing the quality of virtual reality (...
research
∙
01/05/2021
SG-PBFT: a Secure and Highly Efficient Blockchain PBFT Consensus Algorithm for Internet of Vehicles
The Internet of Vehicles (IoV) is an application of the Internet of thin...
research
∙
12/23/2020
Adaptive Precision Training for Resource Constrained Devices
Learn in-situ is a growing trend for Edge AI. Training deep neural netwo...
research
∙
12/06/2020
Fourier-domain Variational Formulation and Its Well-posedness for Supervised Learning
A supervised learning problem is to find a function in a hypothesis func...
research
∙
10/15/2020
On the exact computation of linear frequency principle dynamics and its generalization
Recent works show an intriguing phenomenon of Frequency Principle (F-Pri...
research
∙
07/29/2020
A regularized deep matrix factorized model of matrix completion for image restoration
It has been an important approach of using matrix completion to perform ...
research
∙
07/15/2020
Phase diagram for two-layer ReLU neural networks at infinite-width limit
How neural network behaves during the training over different choices of...
research
∙
07/07/2020
Towards an Understanding of Residual Networks Using Neural Tangent Hierarchy (NTH)
Gradient descent yields zero training loss in polynomial time for deep n...
research
∙
06/28/2020
Two-Layer Neural Networks for Partial Differential Equations: Optimization and Generalization Theory
Deep learning has significantly revolutionized the design of numerical a...
research
∙
06/08/2020
EDCompress: Energy-Aware Model Compression with Dataflow
Edge devices demand low energy consumption, cost and small form factor. ...
research
∙
09/17/2019
Gated Recurrent Units Learning for Optimal Deployment of Visible Light Communications Enabled UAVs
In this paper, the problem of optimizing the deployment of unmanned aeri...
research
∙
06/21/2019
Theory of the Frequency Principle for General Deep Neural Networks
Along with fruitful applications of Deep Neural Networks (DNNs) to reali...
research
∙
05/24/2019
Explicitizing an Implicit Bias of the Frequency Principle in Two-layer Neural Networks
It remains a puzzle that why deep neural networks (DNNs), with more para...
research
∙
05/19/2019