Related papers: Hierarchical Temporal Memory Based on Spin-Neurons…

We extend the reach of temporal computing schemes by developing a memory for multi-channel temporal patterns or "wavefronts." This temporal memory re-purposes conventional one-transistor-one-resistor (1T1R) memristor crossbars for use in an…

Designing lightweight convolutional neural network (CNN) models is an active research area in edge AI. Compute-in-memory (CIM) provides a new computing paradigm to alleviate time and energy consumption caused by data transfer in von Neumann…

The analysis of physiological processes over time are often given by spectrometric or gene expression profiles over time with only few time points but a large number of measured variables. The analysis of such temporal sequences is…

Machine learning methods trained on raw numerical time series data exhibit fundamental limitations such as a high sensitivity to the hyper parameters and even to the initialization of random weights. A combination of a recurrent neural…

Temporal Neural Networks (TNNs) use time as a resource to represent and process information, mimicking the behavior of the mammalian neocortex. This work focuses on implementing TNNs using off-the-shelf digital CMOS technology. A…

Cognitive maps are a proposed concept on how the brain efficiently organizes memories and retrieves context out of them. The entorhinal-hippocampal complex is heavily involved in episodic and relational memory processing, as well as spatial…

In this paper, we propose an efficient predefined structured sparsity-based ex-situ training framework for a hybrid CMOS-memristive neuromorphic hardware for deep neural network to significantly lower the power consumption and computational…

We propose two optimization techniques to minimize memory usage and computation while meeting system timing constraints for real-time classification in wearable systems. Our method derives a hierarchical classifier structure for Support…

The construction of the Hamiltonian matrix \textbf{H} is an essential, yet computationally expensive step in \textit{ab-initio} device simulations based on density-functional theory (DFT). In homogeneous structures, the fact that a unit…

Spiking neural networks, also often referred to as the third generation of neural networks, carry the potential for a massive reduction in memory and energy consumption over traditional, second-generation neural networks. Inspired by the…

In this paper, we develop an in-memory analog computing (IMAC) architecture realizing both synaptic behavior and activation functions within non-volatile memory arrays. Spin-orbit torque magnetoresistive random-access memory (SOT-MRAM)…

Hyperdimensional computing (HDC), utilizing a parallel computing paradigm and efficient learning algorithm, is well-suited for resource-constrained artificial intelligence (AI) applications, such as in edge devices. In-memory computing…

Cognitive maps play a crucial role in facilitating flexible behaviour by representing spatial and conceptual relationships within an environment. The ability to learn and infer the underlying structure of the environment is crucial for…

Recurrent neural networks (RNN) are simple dynamical systems whose computational power has been attributed to their short-term memory. Short-term memory of RNNs has been previously studied analytically only for the case of orthogonal…

We propose a topological framework for memory and inference grounded in the structure of spike-timing dynamics, persistent homology, and the Context-Content Uncertainty Principle (CCUP). Starting from the observation that polychronous…

Cryogenic neuromorphic systems, inspired by the brains unparalleled efficiency, present a promising paradigm for next generation computing architectures.This work introduces a fully integrated neuromorphic framework that combines…

Several problems in neuroimaging and beyond require inference on the parameters of multi-task sparse hierarchical regression models. Examples include M/EEG inverse problems, neural encoding models for task-based fMRI analyses, and climate…

Recent vision and multimodal foundation backbones, such as Transformer families and state-space models like Mamba, have achieved remarkable progress, enabling unified modeling across images, text, and beyond. Despite their empirical…

One of the most challenging obstacles to realizing exascale computing is minimizing the energy consumption of L2 cache, main memory, and interconnects to that memory. For promising cryogenic computing schemes utilizing Josephson junction…

In this pilot study, we propose a neuro-inspired approach that compresses temporal sequences into context-tagged chunks, where each tag represents a recurring structural unit or``community'' in the sequence. These tags are generated during…