English
Related papers

Related papers: Statistical Features in Learning

200 papers

Hebbian meta-learning has recently shown promise to solve hard reinforcement learning problems, allowing agents to adapt to some degree to changes in the environment. However, because each synapse in these approaches can learn a very…

Neural and Evolutionary Computing · Computer Science 2021-06-24 Rasmus Berg Palm , Elias Najarro , Sebastian Risi

Recurrent neural networks in the chaotic regime exhibit complex dynamics reminiscent of high-level cortical activity during behavioral tasks. However, existing training methods for such networks are either biologically implausible, or…

Neurons and Cognition · Quantitative Biology 2015-12-09 Thomas Miconi

Representation learning, and interpreting learned representations, are key areas of focus in machine learning and neuroscience. Both fields generally use representations as a means to understand or improve a system's computations. In this…

Machine Learning · Computer Science 2024-09-24 Andrew Kyle Lampinen , Stephanie C. Y. Chan , Katherine Hermann

Model-based reinforcement learning (MBRL) has shown its advantages in sample-efficiency over model-free reinforcement learning (MFRL). Despite the impressive results it achieves, it still faces a trade-off between the ease of data…

Machine Learning · Computer Science 2020-06-17 Xiaoyu Tan , Chao Qu , Junwu Xiong , James Zhang

A toy model of a neural network in which both Hebbian learning and reinforcement learning occur is studied. The problem of `path interference', which makes that the neural net quickly forgets previously learned input-output relations is…

Disordered Systems and Neural Networks · Physics 2007-05-23 R. J. C. Bosman , W. A. van Leeuwen , B. Wemmenhove

Understanding the dynamics of neural networks in different width regimes is crucial for improving their training and performance. We present an exact solution for the learning dynamics of a one-hidden-layer linear network, with…

Machine Learning · Computer Science 2025-02-24 Yizhou Xu , Liu Ziyin

The gap between the huge volumes of data needed to train artificial neural networks and the relatively small amount of data needed by their biological counterparts is a central puzzle in machine learning. Here, inspired by biological…

Disordered Systems and Neural Networks · Physics 2022-04-19 Miriam Aquaro , Francesco Alemanno , Ido Kanter , Fabrizio Durante , Elena Agliari , Adriano Barra

We develop a methodology to learn finitely generated random iterated function systems from time-series of partial observations using delay embeddings. We obtain a minimal model representation for the observed dynamics, using a hidden…

Dynamical Systems · Mathematics 2025-08-20 Emilia Gibson , Jeroen S. W. Lamb

The set of the fixed points of the Hopfield type network is under investigation. The connection matrix of the network is constructed according to the Hebb rule from the set of memorized patterns which are treated as distorted copies of the…

Disordered Systems and Neural Networks · Physics 2009-10-31 Leonid B. Litinskii

With the emergence of large-scale pre-trained neural networks, methods to adapt such "foundation" models to data-limited downstream tasks have become a necessity. Fine-tuning, preference optimization, and transfer learning have all been…

Machine Learning · Statistics 2025-07-09 Javan Tahir , Surya Ganguli , Grant M. Rotskoff

The ability to exploit prior experience to solve novel problems rapidly is a hallmark of biological learning systems and of great practical importance for artificial ones. In the meta reinforcement learning literature much recent work has…

Forgetting is often seen as an unwanted characteristic in both human and machine learning. However, we propose that forgetting can in fact be favorable to learning. We introduce "forget-and-relearn" as a powerful paradigm for shaping the…

Machine Learning · Computer Science 2022-02-02 Hattie Zhou , Ankit Vani , Hugo Larochelle , Aaron Courville

Inspired by two basic mechanisms in animal visual systems, we introduce a feature transform technique that imposes invariance properties in the training of deep neural networks. The resulting algorithm requires less parameter tuning, trains…

Computer Vision and Pattern Recognition · Computer Science 2021-12-10 Chengxi Ye , Xiong Zhou , Tristan McKinney , Yanfeng Liu , Qinggang Zhou , Fedor Zhdanov

We study the performance of transformers as a function of the number of repetitions of training examples with algorithmically generated datasets. On three problems of mathematics: the greatest common divisor, modular multiplication, and…

Machine Learning · Computer Science 2024-10-10 François Charton , Julia Kempe

To generate coherent responses, language models infer unobserved meaning from their input text sequence. One potential explanation for this capability arises from theories of delay embeddings in dynamical systems, which prove that…

Machine Learning · Computer Science 2024-06-19 Mitchell Ostrow , Adam Eisen , Ila Fiete

There is growing interest in extending average treatment effect (ATE) estimation to incorporate non-tabular data, such as images and text, which may act as sources of confounding. Neglecting these effects risks biased results and flawed…

Machine Learning · Statistics 2025-10-23 Rickmer Schulte , David Rügamer , Thomas Nagler

Many mathematical models of synaptic plasticity have been proposed to explain the diversity of plasticity phenomena observed in biological organisms. These models range from simple interpretations of Hebb's postulate, which suggests that…

Neurons and Cognition · Quantitative Biology 2025-08-05 Danil Tyulmankov

Fully symmetric learning rules for principal component analysis can be derived from a novel objective function suggested in our previous work. We observed that these learning rules suffer from slow convergence for covariance matrices where…

Machine Learning · Statistics 2020-07-21 Ralf Möller

Many machine learning approaches are characterized by information constraints on how they interact with the training data. These include memory and sequential access constraints (e.g. fast first-order methods to solve stochastic…

Machine Learning · Computer Science 2014-10-29 Ohad Shamir

Animals can learn efficiently from a single experience and change their future behavior in response. However, in other instances, animals learn very slowly, requiring thousands of experiences. Here I survey tasks involving fast and slow…

Neurons and Cognition · Quantitative Biology 2022-05-05 Markus Meister