An overview on restricted Boltzmann machines

N Zhang, S Ding, J Zhang, Y Xue - Neurocomputing, 2018 - Elsevier
Abstract The Restricted Boltzmann Machine (RBM) has aroused wide interest in machine
learning fields during the past decade. This review aims to report the recent developments in …

A review of deep learning security and privacy defensive techniques

MI Tariq, NA Memon, S Ahmed… - Mobile Information …, 2020 - Wiley Online Library
In recent past years, Deep Learning presented an excellent performance in different areas
like image recognition, pattern matching, and even in cybersecurity. The Deep Learning has …

PDE-Net 2.0: Learning PDEs from data with a numeric-symbolic hybrid deep network

Z Long, Y Lu, B Dong - Journal of Computational Physics, 2019 - Elsevier
Partial differential equations (PDEs) are commonly derived based on empirical
observations. However, recent advances of technology enable us to collect and store …

On the optimization landscape of neural collapse under mse loss: Global optimality with unconstrained features

J Zhou, X Li, T Ding, C You, Q Qu… - … on Machine Learning, 2022 - proceedings.mlr.press
When training deep neural networks for classification tasks, an intriguing empirical
phenomenon has been widely observed in the last-layer classifiers and features, where (i) …

A geometric analysis of neural collapse with unconstrained features

Z Zhu, T Ding, J Zhou, X Li, C You… - Advances in Neural …, 2021 - proceedings.neurips.cc
We provide the first global optimization landscape analysis of Neural Collapse--an intriguing
empirical phenomenon that arises in the last-layer classifiers and features of neural …

The modern mathematics of deep learning

J Berner, P Grohs, G Kutyniok… - arXiv preprint arXiv …, 2021 - cambridge.org
We describe the new field of the mathematical analysis of deep learning. This field emerged
around a list of research questions that were not answered within the classical framework of …

[HTML][HTML] Universality of deep convolutional neural networks

DX Zhou - Applied and computational harmonic analysis, 2020 - Elsevier
Deep learning has been widely applied and brought breakthroughs in speech recognition,
computer vision, and many other domains. Deep neural network architectures and …

Are all losses created equal: A neural collapse perspective

J Zhou, C You, X Li, K Liu, S Liu… - Advances in Neural …, 2022 - proceedings.neurips.cc
While cross entropy (CE) is the most commonly used loss function to train deep neural
networks for classification tasks, many alternative losses have been developed to obtain …

ReLU deep neural networks and linear finite elements

J He, L Li, J Xu, C Zheng - arXiv preprint arXiv:1807.03973, 2018 - arxiv.org
In this paper, we investigate the relationship between deep neural networks (DNN) with
rectified linear unit (ReLU) function as the activation function and continuous piecewise …

Deep hedging

H Buehler, L Gonon, J Teichmann, B Wood - Quantitative Finance, 2019 - Taylor & Francis
We present a framework for hedging a portfolio of derivatives in the presence of market
frictions such as transaction costs, liquidity constraints or risk limits using modern deep …