English
Related papers

Related papers: Empirical Capacity Model for Self-Attention Neural…

200 papers

Over-parameterized deep neural networks are able to achieve excellent training accuracy while maintaining a small generalization error. It has also been found that they are able to fit arbitrary labels, and this behaviour is referred to as…

Machine Learning · Computer Science 2021-12-17 Futong Liu , Tao Lin , Martin Jaggi

One major obstacle towards AI is the poor ability of models to solve new problems quicker, and without forgetting previously acquired knowledge. To better understand this issue, we study the problem of continual learning, where the model…

Machine Learning · Computer Science 2022-09-14 David Lopez-Paz , Marc'Aurelio Ranzato

The key to a Transformer model is the self-attention mechanism, which allows the model to analyze an entire sequence in a computationally efficient manner. Recent work has suggested the possibility that general attention mechanisms used by…

Machine Learning · Computer Science 2020-01-01 Thomas Dowdell , Hongyu Zhang

For many years now, understanding the brain mechanism has been a great research subject in many different fields. Brain signal processing and especially electroencephalogram (EEG) has recently known a growing interest both in academia and…

Neurons and Cognition · Quantitative Biology 2022-04-18 Victor Delvigne , Hazem Wannous , Jean-Philippe Vandeborre , Laurence Ris , Thierry Dutoit

Memory is fundamental to intelligence, enabling learning, reasoning, and adaptability across biological and artificial systems. While Transformer architectures excel at sequence modeling, they face critical limitations in long-range context…

Machine Learning · Computer Science 2025-08-19 Parsa Omidi , Xingshuai Huang , Axel Laborieux , Bahareh Nikpour , Tianyu Shi , Armaghan Eshaghi

Transformers and their attention mechanism have been revolutionary in the field of Machine Learning. While originally proposed for the language data, they quickly found their way to the image, video, graph, etc. data modalities with various…

Machine Learning · Computer Science 2025-09-22 Saeed Amizadeh , Sara Abdali , Yinheng Li , Kazuhito Koishida

Our work combines aspects of three promising paradigms in machine learning, namely, attention mechanism, energy-based models, and associative memory. Attention is the power-house driving modern deep learning successes, but it lacks clear…

Models trained on a new task typically degrade on prior tasks, a phenomenon known as forgetting. Traditionally, mitigating forgetting has required replaying stored exemplars from prior tasks, which is often impractical. By contrast,…

Machine Learning · Computer Science 2026-05-26 Martin Marek , Dongkyu Cho , Shikai Qiu , Rumi Chunara , Pavel Izmailov , Andrew Gordon Wilson

Transformers have been successfully used in various fields and are becoming the standard tools in computer vision. However, self-attention, a core component of transformers, has a quadratic complexity problem, which limits the use of…

Computer Vision and Pattern Recognition · Computer Science 2022-06-02 Jiuk Hong , Chaehyeon Lee , Soyoun Bang , Heechul Jung

While the Self-Attention mechanism in the Transformer model has proven to be effective in many domains, we observe that it is less effective in more diverse settings (e.g. multimodality) due to the varying granularity of each token and the…

Computer Vision and Pattern Recognition · Computer Science 2024-06-06 Wayner Barrios , SouYoung Jin

Energy based models (EBMs) are appealing due to their generality and simplicity in likelihood modeling, but have been traditionally difficult to train. We present techniques to scale MCMC based EBM training on continuous neural networks,…

Machine Learning · Computer Science 2020-07-01 Yilun Du , Igor Mordatch

The current electroencephalogram (EEG) based deep learning models are typically designed for specific datasets and applications in brain-computer interaction (BCI), limiting the scale of the models and thus diminishing their perceptual…

Machine Learning · Computer Science 2024-06-06 Wei-Bang Jiang , Li-Ming Zhao , Bao-Liang Lu

Mixture models serve as one fundamental tool with versatile applications. However, their training techniques, like the popular Expectation Maximization (EM) algorithm, are notoriously sensitive to parameter initialization and often suffer…

Machine Learning · Computer Science 2023-12-20 Yulai Cong , Sijia Li

Large Language Models (LLMs) have the capacity to store and recall facts. Through experimentation with open-source models, we observe that this ability to retrieve facts can be easily manipulated by changing contexts, even without altering…

Computation and Language · Computer Science 2024-12-02 Yibo Jiang , Goutham Rajendran , Pradeep Ravikumar , Bryon Aragam

One of the predominant methods for training world models is autoregressive prediction in the output space of the next element of a sequence. In Natural Language Processing (NLP), this takes the form of Large Language Models (LLMs)…

Machine Learning · Computer Science 2024-06-14 Alexi Gladstone , Ganesh Nanduru , Md Mofijul Islam , Aman Chadha , Jundong Li , Tariq Iqbal

Exponential random graph models (ERGMs) are very flexible for modeling network formation but pose difficult estimation challenges due to their intractable normalizing constant. Existing methods, such as MCMC-MLE, rely on sequential…

Social and Information Networks · Computer Science 2025-02-05 Angelo Mele

This paper investigates the limitations of transformers for entity-tracking tasks in large language models. We identify a theoretical constraint, showing that transformers require at least $\log_2 (n+1)$ layers to handle entity tracking…

Machine Learning · Computer Science 2024-12-12 Erwan Fagnou , Paul Caillon , Blaise Delattre , Alexandre Allauzen

A major limitation for the broader scope of problems solvable by transformers is the quadratic scaling of computational complexity with input size. In this study, we investigate the recurrent memory augmentation of pre-trained transformer…

Computation and Language · Computer Science 2024-02-07 Aydar Bulatov , Yuri Kuratov , Yermek Kapushev , Mikhail S. Burtsev

Transformers have become central to natural language processing and large language models, but their deployment at scale faces three major challenges. First, the attention mechanism requires massive matrix multiplications and frequent…

Hardware Architecture · Computer Science 2026-01-22 Xiaoxuan Yang , Peilin Chen , Tergel Molom-Ochir , Yiran Chen

Several mechanisms to focus attention of a neural network on selected parts of its input or memory have been used successfully in deep learning models in recent years. Attention has improved image classification, image captioning, speech…

Machine Learning · Computer Science 2017-03-08 Łukasz Kaiser , Samy Bengio