会员服务
Using the Path of Least Resistance to Explain Deep Networks
Arxiv
0+阅读 · 2月24日
Covering Numbers for Deep ReLU Networks with Applications to Function Approximation and Nonparametric Regression
Arxiv
0+阅读 · 3月2日
In-Memory ADC-Based Nonlinear Activation Quantization for Efficient In-Memory Computing
Arxiv
0+阅读 · 3月11日
Modelling and analysis of the 8 filters from the "master key filters hypothesis" for depthwise-separable deep networks in relation to idealized receptive fields based on scale-space theory
Arxiv
0+阅读 · 2月23日
VITAL: More Understandable Feature Visualization through Distribution Alignment and Relevant Information Flow
Arxiv
0+阅读 · 2月17日
Deep networks learn to parse uniform-depth context-free languages from local statistics
Arxiv
0+阅读 · 2月9日
Deep Network Trainability via Persistent Subspace Orthogonality
Arxiv
0+阅读 · 2月11日
Optimal Initialization in Depth: Lyapunov Initialization and Limit Theorems for Deep Leaky ReLU Networks
Arxiv
0+阅读 · 2月11日
Flatness is Necessary, Neural Collapse is Not: Rethinking Generalization via Grokking
Arxiv
0+阅读 · 2月4日
Decoding Generalization from Memorization in Deep Neural Networks
Arxiv
0+阅读 · 2月2日
Pulling Back the Curtain on Deep Networks
Arxiv
0+阅读 · 1月31日
The Hessian of tall-skinny networks is easy to invert
Arxiv
0+阅读 · 1月13日
Unifying Low Dimensional Observations in Deep Learning Through the Deep Linear Unconstrained Feature Model
Arxiv
0+阅读 · 1月26日
Multigrade Neural Network Approximation
Arxiv
0+阅读 · 1月23日
Theory of Minimal Weight Perturbations in Deep Networks and its Applications for Low-Rank Activated Backdoor Attacks
Arxiv
0+阅读 · 1月23日
参考链接
微信扫码咨询专知VIP会员
Top