Related papers: Predictive Associative Memory: Retrieval Beyond Si…
Self-sustained, elevated neuronal activity persisting on time scales of ten seconds or longer is thought to be vital for aspects of working memory, including brain representations of real space. Continuous-attractor neural networks, one of…
Continual learning aims to provide intelligent agents capable of learning multiple tasks sequentially with neural networks. One of its main challenging, catastrophic forgetting, is caused by the neural networks non-optimal ability to learn…
The Pachinko Allocation Machine (PAM) is a deep topic model that allows representing rich correlation structures among topics by a directed acyclic graph over topics. Because of the flexibility of the model, however, approximate inference…
We propose a joint event and temporal relation extraction model with shared representation learning and structured prediction. The proposed method has two advantages over existing work. First, it improves event representation by allowing…
Frequent temporal patterns discovered in time-interval-based multivariate data, although syntactically correct, might be non-transparent: For some pattern instances, there might exist intervals for the same entity that contradict the…
Image-based Joint-Embedding Predictive Architecture (IJEPA) offers an attractive alternative to Masked Autoencoder (MAE) for representation learning using the Masked Image Modeling framework. IJEPA drives representations to capture useful…
Recently, Hopfield and Krotov introduced the concept of {\em dense associative memories} [DAM] (close to spin-glasses with $P$-wise interactions in a disordered statistical mechanical jargon): they proved a number of remarkable features…
The task of a neural associative memory is to retrieve a set of previously memorized patterns from their noisy versions using a network of neurons. An ideal network should have the ability to 1) learn a set of patterns as they arrive, 2)…
The resurgence of near-memory processing (NMP) with the advent of big data has shifted the computation paradigm from processor-centric to memory-centric computing. To meet the bandwidth and capacity demands of memory-centric computing, 3D…
Empathetic response generation aims to comprehend the cognitive and emotional states in dialogue utterances and generate proper responses. Psychological theories posit that comprehending emotional and cognitive states necessitates…
Accomplishing household tasks requires to plan step-by-step actions considering the consequences of previous actions. However, the state-of-the-art embodied agents often make mistakes in navigating the environment and interacting with…
Recent advances in self-supervised visual representation learning have demonstrated the effectiveness of predictive latent-space objectives for learning transferable features. In particular, Image-based Joint-Embedding Predictive…
An associative memory is a framework of content-addressable memory that stores a collection of message vectors (or a dataset) over a neural network while enabling a neurally feasible mechanism to recover any message in the dataset from its…
Reinforcement learning agents often forget details of the past, especially after delays or distractor tasks. Agents with common memory architectures struggle to recall and integrate across multiple timesteps of a past event, or even to…
This paper presents a state-merging algorithm for learning timed languages definable by Event-Recording Automata (ERA) using positive and negative samples in the form of symbolic timed words. Our algorithm, LEAP (Learning Event-recording…
Single-cell foundation models learn by reconstructing masked gene expression, implicitly treating technical noise as signal. With dropout rates exceeding 90%, reconstruction objectives encourage models to encode measurement artifacts rather…
The widespread adoption of Large Language Models (LLMs) has exponentially increased the demand for efficient serving systems. With growing requests and context lengths, key-value (KV)-related operations, including attention computation and…
Conventional computer vision models rely on very deep, feedforward networks processing whole images and trained offline with extensive labeled data. In contrast, biological vision relies on comparatively shallow, recurrent networks that…
Understanding the internal representations of large language models is crucial for ensuring their reliability and safety, with sparse autoencoders (SAEs) emerging as a promising interpretability approach. However, current SAE training…
An autoassociative memory model is a function that, given a set of data points, takes as input an arbitrary vector and outputs the most similar data point from the memorized set. However, popular memory models fail to retrieve images even…