English
Related papers

Related papers: Sparse Attentive Backtracking: Temporal CreditAssi…

200 papers

The recency heuristic in reinforcement learning is the assumption that stimuli that occurred closer in time to an acquired reward should be more heavily reinforced. The recency heuristic is one of the key assumptions made by TD($\lambda$),…

Machine Learning · Computer Science 2024-08-27 Brett Daley , Marlos C. Machado , Martha White

The adaptive fitness of an organism in its ecological niche is highly reliant upon its ability to associate an environmental or internal stimulus with a behavior response through reinforcement. This simple but powerful observation has been…

Neurons and Cognition · Quantitative Biology 2023-12-01 Roy E. Clymer , Sanjeev V. Namjoshi

Training a deep neural network requires a large amount of single-task data and involves a long time-consuming optimization phase. This is not scalable to complex, realistic environments with new unexpected changes. Humans can perform fast…

Neural and Evolutionary Computing · Computer Science 2020-09-04 Tsendsuren Munkhdalai

Humans learn all their life long. They accumulate knowledge from a sequence of learning experiences and remember the essential concepts without forgetting what they have learned previously. Artificial neural networks struggle to learn…

Machine Learning · Computer Science 2020-12-09 Timothée Lesort

Spiking neural networks (SNNs) can utilize spatio-temporal information and have a nature of energy efficiency which is a good alternative to deep neural networks(DNNs). The event-driven information processing makes SNNs can reduce the…

Neural and Evolutionary Computing · Computer Science 2021-12-15 Changqing Xu , Yi Liu , Yintang Yang

We propose a simple technique for encouraging generative RNNs to plan ahead. We train a "backward" recurrent network to generate a given sequence in reverse order, and we encourage states of the forward model to predict cotemporal states of…

Machine Learning · Computer Science 2018-02-27 Dmitriy Serdyuk , Nan Rosemary Ke , Alessandro Sordoni , Adam Trischler , Chris Pal , Yoshua Bengio

Sequence learning, prediction and replay have been proposed to constitute the universal computations performed by the neocortex. The Hierarchical Temporal Memory (HTM) algorithm realizes these forms of computation. It learns sequences in an…

Neurons and Cognition · Quantitative Biology 2022-07-21 Younes Bouhadjar , Dirk J. Wouters , Markus Diesmann , Tom Tetzlaff

Recurrent Neural Networks (RNNs) continue to show outstanding performance in sequence modeling tasks. However, training RNNs on long sequences often face challenges like slow inference, vanishing gradients and difficulty in capturing long…

Artificial Intelligence · Computer Science 2018-02-06 Victor Campos , Brendan Jou , Xavier Giro-i-Nieto , Jordi Torres , Shih-Fu Chang

Biological neural networks learn complex behaviors from sparse, delayed feedback using local synaptic plasticity, yet the mechanisms enabling structured credit assignment remain elusive. In contrast, artificial recurrent networks solving…

Neurons and Cognition · Quantitative Biology 2025-12-12 Dimitra Maoutsa

When using recurrent neural networks (RNNs) it is common practice to apply trained models to sequences longer than those seen in training. This "extrapolating" usage deviates from the traditional statistical learning setup where guarantees…

Machine Learning · Computer Science 2022-03-25 Edo Cohen-Karlik , Avichai Ben David , Nadav Cohen , Amir Globerson

Despite the widespread adoption of Backpropagation algorithm-based Deep Neural Networks, the biological infeasibility of the BP algorithm could potentially limit the evolution of new DNN models. To find a biologically plausible algorithm to…

Neural and Evolutionary Computing · Computer Science 2024-02-29 Jian-Hui Chen , Cheng-Lin Liu , Zuoren Wang

Hybrid architectures combining state-space models with attention have achieved strong efficiency-quality tradeoffs, yet existing approaches either apply attention uniformly or learn static sparse patterns. This misses a key opportunity:…

Machine Learning · Computer Science 2026-02-13 Ibne Farabi Shihab , Sanjeda Akter , Anuj Sharma

Training recurrent neural networks typically relies on backpropagation through time (BPTT). BPTT depends on forward and backward passes to be completed, rendering the network locked to these computations before loss gradients are available.…

Machine Learning · Computer Science 2024-01-17 Joseph Pemberton , Rui Ponte Costa

Transfer learning is a popular practice in deep neural networks, but fine-tuning of large number of parameters is a hard task due to the complex wiring of neurons between splitting layers and imbalance distributions of data in pretrained…

Machine Learning · Computer Science 2017-10-23 Arash Shahriari

The Long Short-Term Memory (LSTM) recurrent neural network is capable of processing complex sequential information since it utilizes special gating schemes for learning representations from long input sequences. It has the potential to…

Computer Vision and Pattern Recognition · Computer Science 2019-05-14 Naifan Zhuang , Guo-Jun Qi , The Duc Kieu , Kien A. Hua

Long Short-Term Memory (LSTM) has achieved state-of-the-art performances on a wide range of tasks. Its outstanding performance is guaranteed by the long-term memory ability which matches the sequential data perfectly and the gating…

Neural and Evolutionary Computing · Computer Science 2019-01-29 Shiwei Liu , Decebal Constantin Mocanu , Mykola Pechenizkiy

Long short-term memory recurrent neural networks (LSTM-RNNs) are considered state-of-the art in many speech processing tasks. The recurrence in the network, in principle, allows any input to be remembered for an indefinite time, a feature…

Audio and Speech Processing · Electrical Eng. & Systems 2020-09-02 Jeroen Zegers , Hugo Van hamme

Fine-tuning pretrained large models to downstream tasks is an important problem, which however suffers from huge memory overhead due to large-scale parameters. This work strives to reduce memory overhead in fine-tuning from perspectives of…

Machine Learning · Computer Science 2024-06-25 Yuchen Yang , Yingdong Shi , Cheems Wang , Xiantong Zhen , Yuxuan Shi , Jun Xu

Greedy algorithms for NLP such as transition based parsing are prone to error propagation. One way to overcome this problem is to allow the algorithm to backtrack and explore an alternative solution in cases where new evidence contradicts…

Computation and Language · Computer Science 2022-06-29 Franck Dary , Maxime Petit , Alexis Nasr

Catastrophic forgetting - the tendency of neural networks to forget previously learned data when learning new information - remains a central challenge in continual learning. In this work, we adopt a behavioral approach, observing a…

Machine Learning · Computer Science 2025-07-08 Guy Hacohen , Tinne Tuytelaars