Related papers: Memory Retrieval in the B-Matrix Neural Network

This paper continues on the work of the B-Matrix approach in hebbian learning proposed by Dr. Kak. It reports the results on methods of improving the memory retrieval capacity of the hebbian neural network which implements the B-Matrix…

This paper reports the results on methods of comparing the memory retrieval capacity of the Hebbian neural network which implements the B-Matrix approach, by using the Widrow-Hoff rule of learning. We then, extend the recently proposed…

This paper reports the results of an experiment on the use of Kak's B-Matrix approach to spreading activity in a Hebbian neural network. Specifically, it concentrates on the memory retrieval from single neurons and compares the performance…

The paper examines the problem of accessing a vector memory from a single neuron in a Hebbian neural network. It begins with the review of the author's earlier method, which is different from the Hopfield model in that it recruits…

We consider the problem of neural association for a network of non-binary neurons. Here, the task is to first memorize a set of patterns using a network of neurons whose states assume values from a finite number of integer levels. Later,…

Deep neural networks have shown superior performance in many regimes to remember familiar patterns with large amounts of data. However, the standard supervised deep learning paradigm is still limited when facing the need to learn new…

Deep neural networks have achieved state-of-the-art results in various vision and/or language tasks. Despite the use of large training datasets, most models are trained by iterating over single input-output pairs, discarding the remaining…

The Hebbian unlearning algorithm, i.e. an unsupervised local procedure used to improve the retrieval properties in Hopfield-like neural networks, is numerically compared to a supervised algorithm to train a linear symmetric perceptron. We…

Ranking models are the main components of information retrieval systems. Several approaches to ranking are based on traditional machine learning algorithms using a set of hand-crafted features. Recently, researchers have leveraged deep…

This paper develops a model that addresses sentence embedding, a hot topic in current natural language processing research, using recurrent neural networks with Long Short-Term Memory (LSTM) cells. Due to its ability to capture long term…

We study the problem of learning associative memory -- a system which is able to retrieve a remembered pattern based on its distorted or incomplete version. Attractor networks provide a sound model of associative memory: patterns are stored…

We introduce a data distribution scheme for $\mathcal{H}$-matrices and a distributed-memory algorithm for $\mathcal{H}$-matrix-vector multiplication. Our data distribution scheme avoids an expensive $\Omega(P^2)$ scheduling procedure used…

Memory data are ubiquitous in Large Language Model (LLM)-based agents (e.g., OpenClaw and Manus). A few recent works have attempted to exploit agents'memory for improving their performance on the question-answering (QA) task, but they lack…

The ability to quickly learn new knowledge (e.g. new classes or data distributions) is a big step towards human-level intelligence. In this paper, we consider scenarios that require learning new classes or data distributions quickly and…

Retrieval augmented models are becoming increasingly popular for computer vision tasks after their recent success in NLP problems. The goal is to enhance the recognition capabilities of the model by retrieving similar examples for the…

We introduce the delta-homology model of memory, a unified framework in which recall, learning, and prediction emerge from cycle closure, the completion of topologically constrained trajectories within the brain's latent manifold. A…

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…

People learn throughout life. However, incrementally updating conventional neural networks leads to catastrophic forgetting. A common remedy is replay, which is inspired by how the brain consolidates memory. Replay involves fine-tuning a…

Meta-learning often referred to as learning-to-learn is a promising notion raised to mimic human learning by exploiting the knowledge of prior tasks but being able to adapt quickly to novel tasks. A plethora of models has emerged in this…

The human brain constantly learns and rapidly adapts to new situations by integrating acquired knowledge and experiences into memory. Developing this capability in machine learning models is considered an important goal of AI research since…