paper-with-me

Papers

Mean Field Theory of Activation Functions in Deep Neural Networks

2018-05-22 · Mirco Milletarí, Thiparat Chotibut, Paolo E. Trevisanutto

We present a Statistical Mechanics (SM) model of deep neural networks, connecting the energy-based and the feed forward networks (FFN) approach. We infer that FFN can be understood as performing three basic steps: encoding, representation validation and propagation. From the meanfield solution of the model, we obtain a set of natural activations -- such as Sigmoid, $\tanh$ and ReLu -- together with the state-of-the-art, Swish; this represents the expected information propagating through the network and tends to ReLu in the limit of zero noise.We study the spectrum of the Hessian on an associated classification task, showing that Swish allows for more consistent performances over a wider range of network architectures.

📄 PDF Abstract BibTeX arXiv:1805.08786

Code (2)

WessZumino/meanfield-theory-of-activation-functions 공식 구현 tf
WessZumino/expectation_propagation tf

Tasks

General Classification

Methods 이 논문이 사용한 방법론

Sigmoid Activation 설명 없음
(FiLe@Against@Claim)How do I file a claim against Expedia? How do I file a claim against Expedia? How Do I File a Claim Against Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Fast Help &…
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…

Similar Papers 제목 키워드 기반

Large Deviation Analysis of Function Sensitivity in Random Deep Neural Networks

2019-10-13 · Bo Li, David Saad

Mean field theory has been successfully used to analyze deep neural networks (DNN) in the infinite size limit. Given the finite size of realistic DNN, we utilize the large deviation theory and path integral analysis to s…

BinarizationSensitivity

A Mean Field Theory of Quantized Deep Networks: The Quantization-Depth Trade-Off

2019-06-03 · NeurIPS 2019 12 · Yaniv Blumenfeld, Dar Gilboa, Daniel Soudry

Reducing the precision of weights and activation functions in neural network training, with minimal impact on performance, is essential for the deployment of these models in resource-constrained environments. We apply me…

Quantization

Function Approximation with Randomly Initialized Neural Networks for Approximate Model Reference Adaptive Control

2023-03-28 · Tyler Lekang, Andrew Lamperski

Classical results in neural network approximation theory show how arbitrary continuous functions can be approximated by networks with a single hidden layer, under mild assumptions on the activation function. However, the…

Mean Field Theory in Deep Metric Learning

2023-06-27 · Takuya Furusawa

In this paper, we explore the application of mean field theory, a technique from statistical physics, to deep metric learning and address the high training complexity commonly associated with conventional metric learning…

Image RetrievalMetric LearningRetrieval

Efficient population coding of sensory stimuli

2022-07-24 · Shuai Shao, Markus Meister, Julijana Gjorgjieva

The efficient coding theory postulates that single cells in a neuronal population should be optimally configured to efficiently encode information about a stimulus subject to biophysical constraints. This poses the quest…