paper-with-me

Papers

Configurable p-Neurons Using Modular p-Bits

2026-01-26 · Saleh Bunaiyan, Mohammad Alsharif, Abdelrahman S. Abdelrahman, Hesham ElSawy, Suraj S. Cheema, Suhaib A. Fahmy, Kerem Y. Camsari, Feras Al-Dirini arxiv

Probabilistic bits (p-bits) have recently been employed in neural networks (NNs) as stochastic neurons with sigmoidal probabilistic activation functions. Nonetheless, there remain a wealth of other probabilistic activation functions that are yet to be explored. Here we re-engineer the p-bit by decoupling its stochastic signal path from its input data path, giving rise to a modular p-bit that enables the realization of probabilistic neurons (p-neurons) with a range of configurable probabilistic activation functions, including a probabilistic version of the widely used Logistic Sigmoid, Tanh and Rectified Linear Unit (ReLU) activation functions. We present spintronic (CMOS + sMTJ) designs that show wide and tunable probabilistic ranges of operation. Finally, we experimentally implement digital-CMOS versions on an FPGA, with stochastic unit sharing, and demonstrate an order of magnitude (10x) saving in required hardware resources compared to conventional digital p-bit implementations.

📄 PDF Abstract BibTeX arXiv:2601.18943

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Configurable Foundation Models: Building LLMs from a Modular Perspective

2024-09-04 · Chaojun Xiao, Zhengyan Zhang, Chenyang Song, Dazhi Jiang 외

Advancements in LLMs have recently unveiled challenges tied to computational efficiency and continual scalability due to their requirements of huge parameters, making the applications and evolution of these models on dev…

Computational EfficiencyMixture-of-Experts

Modular Cognitive Architecture Emerges in Large Language Models

2026-06-27 · Pengrui Han, Jacob Andreas, Evelina Fedorenko, Andrea Gregor de Varda hf

The human brain exhibits a striking degree of functional specialization, with distinct networks supporting language, formal reasoning, reasoning about other minds, and reasoning about the physical world. Is this modular …

Growing Brains: Co-emergence of Anatomical and Functional Modularity in Recurrent Neural Networks

2023-10-11 · Ziming Liu, Mikail Khona, Ila R. Fiete, Max Tegmark

Recurrent neural networks (RNNs) trained on compositional tasks can exhibit functional modularity, in which neurons can be clustered by activity similarity and participation in shared computational subtasks. Unlike brain…

Clustering

HiAER-Spike: Hardware-Software Co-Design for Large-Scale Reconfigurable Event-Driven Neuromorphic Computing

2025-03-20 · Gwenevere Frank, Gopabandhu Hota, Keli Wang, Abhinav Uppal 외

In this work, we present HiAER-Spike, a modular, reconfigurable, event-driven neuromorphic computing platform designed to execute large spiking neural networks with up to 160 million neurons and 40 billion synapses - rou…

Cloud Computing

HiAER-Spike Software-Hardware Reconfigurable Platform for Event-Driven Neuromorphic Computing at Scale

2026-02-20 · Gwenevere Frank, Gopabandhu Hota, Keli Wang, Christopher Deng 외 arxiv

In this work, we present HiAER-Spike, a modular, reconfigurable, event-driven neuromorphic computing platform designed to execute large spiking neural networks with up to 160 million neurons and 40 billion synapses - rou…