中文
相关论文

相关论文: Boltzmann Reinforcement Learning for Noise resilie…

200 篇论文

Analog computing hardwares, such as Processing-in-memory (PIM) accelerators, have gradually received more attention for accelerating the neural network computations. However, PIM accelerators often suffer from intrinsic noise in the…

计算机视觉与模式识别 · 计算机科学 2020-11-25 Li-Huang Tsai , Shih-Chieh Chang , Yu-Ting Chen , Jia-Yu Pan , Wei Wei , Da-Cheng Juan

Ising machines are a promising non-von-Neumann computational concept for neural network training and combinatorial optimization. However, while various neural networks can be implemented with Ising machines, their inability to perform fast…

应用物理 · 物理学 2022-10-05 Fabian Böhm , Diego Alonso-Urquijo , Guy Verschaffelt , Guy Van der Sande

Verification of binary neural network (BNN) robustness is NP-hard, as it can be formulated as a combinatorial search for an adversarial perturbation that induces misclassification. Exact verification methods therefore scale poorly with…

新兴技术 · 计算机科学 2026-03-09 Madhav Vadlamani , Rahul Singh , Yuyao Kong , Zheng Zhang , Shimeng Yu

The coherent Ising machine (CIM) is a quantum-inspired computing platform that leverages optical parametric oscillation dynamics to solve combinatorial optimization problems by searching for the ground state of an Ising Hamiltonian.…

量子物理 · 物理学 2025-09-18 Yan Chen Jiang , Lu Ma , Chuan Wang , Tie Jun Wang

Bayesian Neural Networks (BNNs) provide superior estimates of uncertainty by generating an ensemble of predictive distributions. However, inference via ensembling is resource-intensive, requiring additional entropy sources to generate…

新兴技术 · 计算机科学 2025-05-20 Prabodh Katti , Clement Ruah , Osvaldo Simeone , Bashir M. Al-Hashimi , Bipin Rajendran

We show that the nonlinear stochastic dynamics of a measurement-feedback-based coherent Ising machine (MFB-CIM) in the presence of quantum noise can be exploited to sample degenerate ground and low-energy spin configurations of the Ising…

We introduce a universal theory of phase auto-oscillators driven by a bi harmonic signal (having frequency components close to single and double of the free-running oscillator frequency) with noise. With it, we show how deterministic phase…

Ising machines are novel computing devices for the energy minimization of Ising models. These combinatorial optimization problems are of paramount importance for science and technology, but remain difficult to tackle on large scale by…

光学 · 物理学 2020-04-28 Davide Pierangeli , Giulia Marcucci , Daniel Brunner , Claudio Conti

Optimization problems, particularly NP-Hard Combinatorial Optimization problems, are some of the hardest computing problems with no known polynomial time algorithm existing. Recently there has been interest in using dedicated hardware to…

硬件体系结构 · 计算机科学 2020-10-15 Saavan Patel , Lili Chen , Philip Canoza , Sayeef Salahuddin

Blind beamforming has emerged as a promising approach to configure reconfigurable intelligent surfaces (RISs) without relying on channel state information (CSI) or geometric models, making it directly compatible with commodity hardware. In…

信号处理 · 电气工程与系统科学 2025-11-10 Son Dinh-Van , Nam Phuong Tran , Matthew D. Higgins

The Boltzmann Machine (BM) is a neural network composed of stochastically firing neurons that can learn complex probability distributions by adapting the synaptic interactions between the neurons. BMs represent a very generic class of…

介观与纳米尺度物理 · 物理学 2021-09-16 Brian Kiraly , Elze J. Knol , Hilbert J. Kappen , Alexander A. Khajetoorians

Analog Compute-In-Memory (CIM) architectures promise significant energy efficiency gains for neural network inference, but suffer from complex hardware-induced noise that poses major challenges for deployment. While noise-aware training…

机器学习 · 计算机科学 2025-08-19 Yuannuo Feng , Wenyong Zhou , Yuexi Lyu , Yixiang Zhang , Zhengwu Liu , Ngai Wong , Wang Kang

Analog computing using bosonic computational states is a leading approach to surpassing the computational speed and energy limitations of von Neumann architectures. But the challenges of manufacturing large-scale photonic integrated…

光学 · 物理学 2025-07-22 Farhad Khosravi , Martin Perreault , Artur Scherer , Pooya Ronagh

Recent reinforcement learning algorithms, though achieving impressive results in various fields, suffer from brittle training effects such as regression in results and high sensitivity to initialization and parameters. We claim that some of…

机器学习 · 计算机科学 2019-05-27 Refael Vivanti , Talya D. Sohlberg-Baris , Shlomo Cohen , Orna Cohen

Analog in-memory computing (AIMC) is a promising compute paradigm to improve speed and power efficiency of neural network inference beyond the limits of conventional von Neumann-based architectures. However, AIMC introduces fundamental…

Recent advances in deep learning and neural networks have led to an increased interest in the application of generative models in statistical and condensed matter physics. In particular, restricted Boltzmann machines (RBMs) and variational…

无序系统与神经网络 · 物理学 2020-06-09 Francesco D'Angelo , Lucas Böttcher

We compare Ising ({-1,+1}) and QUBO ({0,1}) encodings for Boltzmann machine learning under a controlled protocol that fixes the model, sampler, and step size. Exploiting the identity that the Fisher information matrix (FIM) equals the…

机器学习 · 计算机科学 2025-10-16 Yasushi Hasegawa , Masayuki Ohzeki

A hybrid quantum-classical method for learning Boltzmann machines (BM) for a generative and discriminative task is presented. Boltzmann machines are undirected graphs with a network of visible and hidden nodes where the former is used as…

量子物理 · 物理学 2022-07-21 Siddhartha Srivastava , Veera Sundararaghavan

Decades of exponential scaling in high performance computing (HPC) efficiency is coming to an end. Transistor based logic in complementary metal-oxide semiconductor (CMOS) technology is approaching physical limits beyond which further…

机器学习 · 计算机科学 2024-02-01 Fiona Knoll , John T. Daly , Jess J. Meyer

The disparity between the computational demands of deep learning and the capabilities of compute hardware is expanding drastically. Although deep learning achieves remarkable performance in countless tasks, its escalating requirements for…

机器学习 · 计算机科学 2025-09-12 Xiao Wang , Hendrik Borras , Bernhard Klein , Holger Fröning
‹ 上一页 1 2 3 10 下一页 ›