English
Related papers

Related papers: About Learning in Recurrent Bistable Gradient Netw…

200 papers

Recurrent neural network grammars (RNNG) are generative models of language which jointly model syntax and surface structure by incrementally generating a syntax tree and sentence in a top-down, left-to-right order. Supervised RNNGs achieve…

Computation and Language · Computer Science 2019-08-06 Yoon Kim , Alexander M. Rush , Lei Yu , Adhiguna Kuncoro , Chris Dyer , Gábor Melis

Humans learn continually throughout their lifespan by accumulating diverse knowledge and fine-tuning it for future tasks. When presented with a similar goal, neural networks suffer from catastrophic forgetting if data distributions across…

Machine Learning · Computer Science 2022-09-19 Dupati Srikar Chandra , Sakshi Varshney , P. K. Srijith , Sunil Gupta

The dynamics of gradient-based training in neural networks often exhibit nontrivial structures; hence, understanding them remains a central challenge in theoretical machine learning. In particular, a concept of feature unlearning, in which…

Machine Learning · Computer Science 2026-02-10 Shota Imai , Sota Nishiyama , Masaaki Imaizumi

We introduce a new class of networks that grow by enhanced redirection. Nodes are introduced sequentially, and each either attaches to a randomly chosen target node with probability 1-r or to the ancestor of the target with probability r,…

Statistical Mechanics · Physics 2013-11-14 Alan Gabel , P. L. Krapivsky , S. Redner

Error backpropagation is a highly effective mechanism for learning high-quality hierarchical features in deep networks. Updating the features or weights in one layer, however, requires waiting for the propagation of error signals from…

Neural and Evolutionary Computing · Computer Science 2017-11-21 Hesham Mostafa , Vishwajith Ramesh , Gert Cauwenberghs

Discrete structures are currently second-class in differentiable programming. Since functions over discrete structures lack overt derivatives, differentiable programs do not differentiate through them and limit where they can be used. For…

Programming Languages · Computer Science 2025-11-20 Joey Velez-Ginorio , Nada Amin , Konrad Kording , Steve Zdancewic

We study associative memory of an oscillator neural network with distributed native frequencies. The model is based on the use of the Hebb learning rule with random patterns ($\xi_i^{\mu}=\pm 1$), and the distribution function of native…

Disordered Systems and Neural Networks · Physics 2009-10-31 Michiko Yamana , Masatoshi Shiino , Masahiko Yoshioka

We consider artificial neurons which will update their weight coefficients with an internal rule based on backpropagation, rather than using it as an external training procedure. To achieve this we include the backpropagation error estimate…

Neural and Evolutionary Computing · Computer Science 2018-08-07 M. N. Nazarov

The proper initialization of weights is crucial for the effective training and fast convergence of deep neural networks (DNNs). Prior work in this area has mostly focused on balancing the variance among weights per layer to maintain…

Machine Learning · Computer Science 2020-06-05 Maciej Skorski , Alessandro Temperoni , Martin Theobald

We describe a class of systems theory based neural networks called "Network Of Recurrent neural networks" (NOR), which introduces a new structure level to RNN related models. In NOR, RNNs are viewed as the high-level neurons and are used to…

Neural and Evolutionary Computing · Computer Science 2017-10-11 Chao-Ming Wang

Recurrent neural networks (RNNs) are known to be difficult to train due to the gradient vanishing and exploding problems and thus difficult to learn long-term patterns and construct deep networks. To address these problems, this paper…

Computer Vision and Pattern Recognition · Computer Science 2020-12-10 Shuai Li , Wanqing Li , Chris Cook , Yanbo Gao

A locally iterative learning (LIL) rule is adapted to a model of the associative memory based on the evolving recurrent-type neural networks composed of growing neurons. There exist extremely different scale parameters of time, the…

adap-org · Physics 2008-02-03 Sh. Fujita , H. Nishimura

Continual learning could shift the machine learning paradigm from data centric to model centric. A continual learning model needs to scale efficiently to handle semantically different datasets, while avoiding unnecessary growth. We…

Machine Learning · Computer Science 2020-10-13 Ahmad Berjaoui

Hypernetworks are meta neural networks that generate weights for a main neural network in an end-to-end differentiable manner. Despite extensive applications ranging from multi-task learning to Bayesian deep learning, the problem of…

Machine Learning · Computer Science 2023-12-15 Oscar Chang , Lampros Flokas , Hod Lipson

The human brain is a complex system that is fascinating scientists since a long time. Its remarkable capabilities include categorization of concepts, retrieval of memories and creative generation of new examples. At the same time, modern…

Disordered Systems and Neural Networks · Physics 2024-10-10 Enrico Ventura

In general, the behavior of large and complex aggregates of elementary components can not be understood nor extrapolated from the properties of a few components. The brain is a good example of this type of networked systems where some…

Chaotic Dynamics · Physics 2012-08-02 Ricardo Lopez-Ruiz , Daniele Fournier-Prunaret

Countless learning tasks require dealing with sequential data. Image captioning, speech synthesis, and music generation all require that a model produce outputs that are sequences. In other domains, such as time series prediction, video…

Machine Learning · Computer Science 2015-10-20 Zachary C. Lipton , John Berkowitz , Charles Elkan

Recurrent neural network grammars (RNNG) are a recently proposed probabilistic generative modeling family for natural language. They show state-of-the-art language modeling and parsing performance. We investigate what information they…

Computation and Language · Computer Science 2017-01-12 Adhiguna Kuncoro , Miguel Ballesteros , Lingpeng Kong , Chris Dyer , Graham Neubig , Noah A. Smith

We introduce a parameter sharing scheme, in which different layers of a convolutional neural network (CNN) are defined by a learned linear combination of parameter tensors from a global bank of templates. Restricting the number of templates…

Machine Learning · Computer Science 2019-03-15 Pedro Savarese , Michael Maire

Recurrent neural nets are widely used for predicting temporal data. Their inherent deep feedforward structure allows learning complex sequential patterns. It is believed that top-down feedback might be an important missing ingredient which…

Machine Learning · Computer Science 2016-10-20 Kamil M Rocki