Hopfield network | EPFL Graph Search

A Hopfield network (or Amari-Hopfield network, Ising model of a neural network or Ising–Lenz–Little model) is a form of recurrent artificial neural network and a type of spin glass system popularised by John Hopfield in 1982 as described by Shun'ichi Amari in 1972 and by Little in 1974 based on Ernst Ising's work with Wilhelm Lenz on the Ising model. Hopfield networks serve as content-addressable ("associative") memory systems with binary threshold nodes, or with continuous variables. Hopfield networks also provide a model for understanding human memory. The Ising model of a recurrent neural network as a learning memory model was first proposed by Shun'ichi Amari in 1972 and then by William A. Little in 1974, who was acknowledged by Hopfield in his 1982 paper. Networks with continuous dynamics were developed by Hopfield in his 1984 paper. A major advance in memory storage capacity was developed by Krotov and Hopfield in 2016 through a change in network dynamics and energy function. This idea was further extended by Demircigil and collaborators in 2017. The continuous dynamics of large memory capacity models was developed in a series of papers between 2016 and 2020. Large memory storage capacity Hopfield Networks are now called Dense Associative Memories or modern Hopfield networks. The units in Hopfield nets are binary threshold units, i.e. the units only take on two different values for their states, and the value is determined by whether or not the unit's input exceeds its threshold . Discrete Hopfield nets describe relationships between binary (firing or not-firing) neurons . At a certain time, the state of the neural net is described by a vector , which records which neurons are firing in a binary word of bits. The interactions between neurons have units that usually take on values of 1 or −1, and this convention will be used throughout this article. However, other literature might use units that take values of 0 and 1. These interactions are "learned" via Hebb's law of association, such that, for a certain state and distinct nodes but .

Towards Verifiable, Generalizable and Efficient Robust Deep Neural Networks.

Chen Liu

In the last decade, deep neural networks have achieved tremendous success in many fields of machine learning.However, they are shown vulnerable against adversarial attacks: well-designed, yet imperceptible, perturbations can make the state-of-the-art deep neural networks output incorrect results.Understanding adversarial attacks and designing algorithms to make deep neural networks robust against these attacks are key steps to building reliable artificial intelligence in real-life applications.In this thesis, we will first formulate the robust learning problem.Based on the notations of empirical robustness and verified robustness, we design new algorithms to achieve both of these types of robustness.Specifically, we investigate the robust learning problem from the optimization perspectives.Compared with classic empirical risk minimization, we show the slow convergence and large generalization gap in robust learning.Our theoretical and numerical analysis indicates that these challenges arise, respectively, from non-smooth loss landscapes and model's fitting hard adversarial instances.Our insights shed some light on designing algorithms for mitigating these challenges.Robust learning has other challenges, such as large model capacity requirements and high computational complexity.To solve the model capacity issue, we combine robust learning with model compression.We design an algorithm to obtain sparse and binary neural networks and make it robust.To decrease the computational complexity, we accelerate the existing adversarial training algorithm and preserve its performance stability.In addition to making models robust, our research provides other benefits.Our methods demonstrate that robust models, compared with non-robust ones, usually utilize input features in a way more similar to the way human beings use them, hence the robust models are more interpretable.To obtain verified robustness, our methods indicate the geometric similarity of the decision boundaries near data points.Our approaches towards reliable artificial intelligence can not only render deep neural networks more robust in safety-critical applications but also make us better aware of how they work.

EPFL2022

Parallel retrieval of correlated patterns: From Hopfield networks to Boltzmann machines

Andrea De Antoni

In this work, we first revise some extensions of the standard Hopfield model in the low storage limit, namely the correlated attractor case and the multitasking case recently introduced by the authors. The former case is based on a modification of the Hebbian prescription, which induces a coupling between consecutive patterns and this effect is tuned by a parameter a. In the latter case, dilution is introduced in pattern entries, in such a way that a fraction d of them is blank. Then, we merge these two extensions to obtain a system able to retrieve several patterns in parallel and the quality of retrieval, encoded by the set of Mattis magnetizations {m(mu)}, is reminiscent of the correlation among patterns. By tuning the parameters d and a, qualitatively different outputs emerge, ranging from highly hierarchical to symmetric. The investigations are accomplished by means of both numerical simulations and statistical mechanics analysis, properly adapting a novel technique originally developed for spin glasses, i.e. the Hamilton-Jacobi interpolation, with excellent agreement. Finally, we show the thermodynamical equivalence of this associative network with a (restricted) Boltzmann machine and study its stochastic dynamics to obtain even a dynamical picture, perfectly consistent with the static scenario earlier discussed. (c) 2012 Elsevier Ltd. All rights reserved.

Elsevier2013

Extended Hopfield Network for Sequence Learning: Application to Gesture Recognition

Aude Billard, Micha Hersch, André Maurer

In this paper, we extend the Hopfield Associative Memory for storing multiple sequences of varying duration. We apply the model for learning, recognizing and encoding a set of human gestures. We measure systematically the performance of the model against noise.

2005

Towards Verifiable, Generalizable and Efficient Robust Deep Neural Networks.

Chen Liu

EPFL2022