Training Deep Boltzmann Networks with Sparse Ising Machines

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Niazi, Shaila, Aadit, Navid Anjum, Mohseni, Masoud, Chowdhury, Shuvro, Qin, Yao, Camsari, Kerem Y.
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913369515098112
author Niazi, Shaila
Aadit, Navid Anjum
Mohseni, Masoud
Chowdhury, Shuvro
Qin, Yao
Camsari, Kerem Y.
author_facet Niazi, Shaila
Aadit, Navid Anjum
Mohseni, Masoud
Chowdhury, Shuvro
Qin, Yao
Camsari, Kerem Y.
contents The slowing down of Moore's law has driven the development of unconventional computing paradigms, such as specialized Ising machines tailored to solve combinatorial optimization problems. In this paper, we show a new application domain for probabilistic bit (p-bit) based Ising machines by training deep generative AI models with them. Using sparse, asynchronous, and massively parallel Ising machines we train deep Boltzmann networks in a hybrid probabilistic-classical computing setup. We use the full MNIST and Fashion MNIST (FMNIST) dataset without any downsampling and a reduced version of CIFAR-10 dataset in hardware-aware network topologies implemented in moderately sized Field Programmable Gate Arrays (FPGA). For MNIST, our machine using only 4,264 nodes (p-bits) and about 30,000 parameters achieves the same classification accuracy (90%) as an optimized software-based restricted Boltzmann Machine (RBM) with approximately 3.25 million parameters. Similar results follow for FMNIST and CIFAR-10. Additionally, the sparse deep Boltzmann network can generate new handwritten digits and fashion products, a task the 3.25 million parameter RBM fails at despite achieving the same accuracy. Our hybrid computer takes a measured 50 to 64 billion probabilistic flips per second, which is at least an order of magnitude faster than superficially similar Graphics and Tensor Processing Unit (GPU/TPU) based implementations. The massively parallel architecture can comfortably perform the contrastive divergence algorithm (CD-n) with up to n = 10 million sweeps per update, beyond the capabilities of existing software implementations. These results demonstrate the potential of using Ising machines for traditionally hard-to-train deep generative Boltzmann networks, with further possible improvement in nanodevice-based realizations.
format Preprint
id arxiv_https___arxiv_org_abs_2303_10728
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Training Deep Boltzmann Networks with Sparse Ising Machines
Niazi, Shaila
Aadit, Navid Anjum
Mohseni, Masoud
Chowdhury, Shuvro
Qin, Yao
Camsari, Kerem Y.
Emerging Technologies
Machine Learning
Neural and Evolutionary Computing
The slowing down of Moore's law has driven the development of unconventional computing paradigms, such as specialized Ising machines tailored to solve combinatorial optimization problems. In this paper, we show a new application domain for probabilistic bit (p-bit) based Ising machines by training deep generative AI models with them. Using sparse, asynchronous, and massively parallel Ising machines we train deep Boltzmann networks in a hybrid probabilistic-classical computing setup. We use the full MNIST and Fashion MNIST (FMNIST) dataset without any downsampling and a reduced version of CIFAR-10 dataset in hardware-aware network topologies implemented in moderately sized Field Programmable Gate Arrays (FPGA). For MNIST, our machine using only 4,264 nodes (p-bits) and about 30,000 parameters achieves the same classification accuracy (90%) as an optimized software-based restricted Boltzmann Machine (RBM) with approximately 3.25 million parameters. Similar results follow for FMNIST and CIFAR-10. Additionally, the sparse deep Boltzmann network can generate new handwritten digits and fashion products, a task the 3.25 million parameter RBM fails at despite achieving the same accuracy. Our hybrid computer takes a measured 50 to 64 billion probabilistic flips per second, which is at least an order of magnitude faster than superficially similar Graphics and Tensor Processing Unit (GPU/TPU) based implementations. The massively parallel architecture can comfortably perform the contrastive divergence algorithm (CD-n) with up to n = 10 million sweeps per update, beyond the capabilities of existing software implementations. These results demonstrate the potential of using Ising machines for traditionally hard-to-train deep generative Boltzmann networks, with further possible improvement in nanodevice-based realizations.
title Training Deep Boltzmann Networks with Sparse Ising Machines
topic Emerging Technologies
Machine Learning
Neural and Evolutionary Computing
url https://arxiv.org/abs/2303.10728