English
Related papers

Related papers: Massive Redundancy in Gradient Transport Enables S…

200 papers

For three decades online recurrent learning has been assumed to require propagating a Jacobian tensor through the network's dynamics at $O(n^4)$ per step. We show it doesn't. Dropping the propagation entirely ($d=0$, $O(n^2)$ memory)…

Machine Learning · Computer Science 2026-04-29 Aur Shalev Merin

Current methods for training recurrent neural networks are based on backpropagation through time, which requires storing a complete history of network states, and prohibits updating the weights `online' (after every timestep). Real Time…

Machine Learning · Computer Science 2020-06-15 Jacob Menick , Erich Elsen , Utku Evci , Simon Osindero , Karen Simonyan , Alex Graves

Backpropagation through time (BPTT) is the standard algorithm for training recurrent neural networks (RNNs), which requires separate simulation phases for the forward and backward passes for inference and learning, respectively. Moreover,…

Machine Learning · Computer Science 2023-03-13 Anand Subramoney

Recurrent neural networks (RNNs) are commonly trained with the truncated backpropagation-through-time (TBPTT) algorithm. For the purposes of computational tractability, the TBPTT algorithm truncates the chain rule and calculates the…

Machine Learning · Computer Science 2025-01-15 Samuel Chun-Hei Lam , Justin Sirignano , Konstantinos Spiliopoulos

Despite all the impressive advances of recurrent neural networks, sequential data is still in need of better modelling. Truncated backpropagation through time (TBPTT), the learning algorithm most widely used in practice, suffers from the…

Machine Learning · Computer Science 2018-12-07 Asier Mujika , Florian Meier , Angelika Steger

Recent advances in the sparse neural network literature have made it possible to prune many large feed forward and convolutional networks with only a small quantity of data. Yet, these same techniques often falter when applied to the…

Machine Learning · Computer Science 2019-12-03 Matthew Shunshi Zhang , Bradly Stadie

Constructing states from sequences of observations is an important component of reinforcement learning agents. One solution for state construction is to use recurrent neural networks. Back-propagation through time (BPTT), and real-time…

Machine Learning · Computer Science 2023-11-23 Khurram Javed , Haseeb Shah , Rich Sutton , Martha White

Recurrent networks are typically trained with backpropagation through time (BPTT). However, BPTT requires storing the history of all states in the network and then replaying them sequentially backwards in time. This computation appears…

Machine Learning · Computer Science 2026-01-01 Beren Millidge

Real-time recurrent learning (RTRL) for sequence-processing recurrent neural networks (RNNs) offers certain conceptual advantages over backpropagation through time (BPTT). RTRL requires neither caching past activations nor truncating…

Machine Learning · Computer Science 2024-02-29 Kazuki Irie , Anand Gopalakrishnan , Jürgen Schmidhuber

We introduce the "NoBackTrack" algorithm to train the parameters of dynamical systems such as recurrent neural networks. This algorithm works in an online, memoryless setting, thus requiring no backpropagation through time, and is scalable,…

Neural and Evolutionary Computing · Computer Science 2015-11-24 Yann Ollivier , Corentin Tallec , Guillaume Charpiat

This paper presents a transfer learning approach which enables fast and efficient adaptation of Recurrent Neural Network (RNN) models of dynamical systems. A nominal RNN model is first identified using available measurements. The system…

Machine Learning · Computer Science 2022-01-24 Marco Forgione , Aneri Muni , Dario Piga , Marco Gallieri

Deep neural networks, particularly in vision tasks, are notably susceptible to adversarial perturbations. To overcome this challenge, developing a robust classifier is crucial. In light of the recent advancements in the robustness of…

Computer Vision and Pattern Recognition · Computer Science 2024-02-14 Binh M. Le , Shahroz Tariq , Simon S. Woo

One of the central goals of Recurrent Neural Networks (RNNs) is to learn long-term dependencies in sequential data. Nevertheless, the most popular training method, Truncated Backpropagation through Time (TBPTT), categorically forbids…

Machine Learning · Computer Science 2019-05-20 Frederik Benzing , Marcelo Matheus Gauy , Asier Mujika , Anders Martinsson , Angelika Steger

Learning expressive probabilistic models correctly describing the data is a ubiquitous problem in machine learning. A popular approach for solving it is mapping the observations into a representation space with a simple joint distribution,…

Machine Learning · Statistics 2020-10-28 Luigi Gresele , Giancarlo Fissore , Adrián Javaloy , Bernhard Schölkopf , Aapo Hyvärinen

Recurrent neural networks (RNNs) provide state-of-the-art performance in processing sequential data but are memory intensive to train, limiting the flexibility of RNN models which can be trained. Reversible RNNs---RNNs for which the…

Machine Learning · Computer Science 2018-10-26 Matthew MacKay , Paul Vicol , Jimmy Ba , Roger Grosse

Sparse training is a natural idea to accelerate the training speed of deep neural networks and save the memory usage, especially since large modern neural networks are significantly over-parameterized. However, most of the existing methods…

Machine Learning · Computer Science 2021-11-11 Xiao Zhou , Weizhong Zhang , Zonghao Chen , Shizhe Diao , Tong Zhang

While backpropagation--reverse-mode automatic differentiation--has been extraordinarily successful in deep learning, it requires two passes (forward and backward) through the neural network and the storage of intermediate activations.…

Machine Learning · Computer Science 2025-11-06 Daniel Wang , Evan Markou , Dylan Campbell

Streaming reinforcement learning has emerged as an online learning paradigm that conforms to the restrictions of natural learning agents that process data incrementally, i.e. with a batch size of 1 and no replay buffer. While streaming RL…

Machine Learning · Computer Science 2026-05-26 Noah Farr , Aryaman Reddi , Carlo D'Eramo , Jan Peters

Recurrent Neural Networks (RNNs) are useful in temporal sequence tasks. However, training RNNs involves dense matrix multiplications which require hardware that can support a large number of arithmetic operations and memory accesses.…

Machine Learning · Computer Science 2023-12-18 Xi Chen , Chang Gao , Zuowen Wang , Longbiao Cheng , Sheng Zhou , Shih-Chii Liu , Tobi Delbruck

We present a sparse analogue to stochastic gradient descent that is guaranteed to perform well under similar conditions to the lasso. In the linear regression setup with irrepresentable noise features, our algorithm recovers the support set…

Statistics Theory · Mathematics 2014-12-16 Jacob Steinhardt , Stefan Wager , Percy Liang
‹ Prev 1 2 3 10 Next ›