Shaila Niazi

Shaila Niazi

Auto-generated profile, based on publicly available information

Shaila Niazi

Department of Electrical and Computer Engineering, University of California at Santa Barbara, Santa Barbara, CA, USA

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
14 March 2023 in IEEE Journal on Exploratory Solid-State Computational Devices and Circuits
Verified
Journal Article
Open access
SCShuvro Chowdhury
Shuvro Chowdhury
AGAndrea Grimaldi
Andrea Grimaldi
NANavid Anjum Aadit
Navid Anjum Aadit
SNShaila Niazi
Shaila Niazi
MMMasoud Mohseni
Masoud Mohseni
KCKerem Y. Camsari
Kerem Y. Camsari
The transistor celebrated its 75 th birthday in 2022. The continued scaling of the transistor defined by Moore’s Law continues, albeit at a slower pace. Meanwhile, computing demands and energy consumption required by modern artificial intelligence (AI) algorithms have skyrocketed. As an alternative to scaling transistors for general-purpose computing, the integration of transistors with unconventional technologies has emerged as a promising path for domain-specific computing. In this article, we provide a full-stack review of probabilistic computing with p-bits as a representative example of the energy-efficient and domain-specific computing movement. We argue that p-bits could be used to build energy-efficient probabilistic systems, tailored for probabilistic algorithms and applications. From hardware, architecture, and algorithmic perspectives, we outline the main applications of probabilistic computers ranging from probabilistic machine learning and AI to combinatorial optimization and quantum simulation. Combining emerging nanodevices with the existing CMOS ecosystem will lead to probabilistic computers with orders of magnitude improvements in energy efficiency and probabilistic sampling, potentially unlocking previously unexplored regimes for powerful probabilistic algorithms.

17 June 2024 in Nature Electronics
Verified
Journal Article
Closed access
PDF file
SNShaila Niazi
Shaila Niazi
SCShuvro Chowdhury
Shuvro Chowdhury
NANavid Anjum Aadit
Navid Anjum Aadit
MMMasoud Mohseni
Masoud Mohseni
YQYao Qin
Yao Qin
KCKerem Y. Camsari
Kerem Y. Camsari

28 April 2025 in IEEE Transactions on Electron Devices
Verified
Journal Article
Closed access
TPTanvir H. Pantha
Tanvir H. Pantha
AKAbhishek Khanna
Abhishek Khanna
HYHuacheng Ye
Huacheng Ye
SNShaila Niazi
Shaila Niazi
MKMiriyala P. Kamal
Miriyala P. Kamal
SDSourav Dutta
Sourav Dutta
Recent advancements in Ising machines present an exciting new paradigm for addressing computationally intensive problems with superior energy efficiency and speed compared to conventional digital computers. Despite these promising developments, many real-world problems demand high connectivity, a requirement that exceeds the capabilities of current CMOS-based Ising machine hardware. To overcome this connectivity bottleneck, we propose a novel approach leveraging programmable multibit back-end-of-line (BEOL) ferroelectric field-effect transistor (FeFETs) capable of monolithic 3-D stacking. We experimentally demonstrate a 10-node, 24-coupling Ising machine utilizing dual-gated BEOL FeFETs. This platform enables real-time reconfigurability and supports diverse computational workloads, including combinatorial optimization problems and energy-based learning. Our platform demonstrates robust error-resilient computation with minimal accuracy degradation, even under high endurance conditions of up to 10 billion read and write cycles. This resilience is critical for both read-intensive forward problems and write-intensive inverse or learning problems. To evaluate the performance and area gains, we benchmark the proposed FeFET-based architecture against traditional CMOS implementations. The results reveal significant advantages for FeFET technology, including an 8.2× increase in coupling density, an 11× improvement in energy efficiency, and a 2.1× reduction in latency.

24 January 2024 in arXiv
Verified
Preprint
Open access
PDF file
SNShaila Niazi
Shaila Niazi
NANavid Anjum Aadit
Navid Anjum Aadit
MMMasoud Mohseni
Masoud Mohseni
SCShuvro Chowdhury
Shuvro Chowdhury
YQYao Qin
Yao Qin
KCKerem Y. Camsari
Kerem Y. Camsari
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.

3 January 2024 in arXiv
Verified
Preprint
Open access
PDF file
SCShuvro Chowdhury
Shuvro Chowdhury
SNShaila Niazi
Shaila Niazi
KCKerem Y. Camsari
Kerem Y. Camsari
Despite their appeal as physics-inspired, energy-based and generative nature, general Boltzmann Machines (BM) are considered intractable to train. This belief led to simplified models of BMs with restricted intralayer connections or layer-by-layer training of deep BMs. Recent developments in domain-specific hardware -- specifically probabilistic computers (p-computer) with probabilistic bits (p-bit) -- may change established wisdom on the tractability of deep BMs. In this paper, we show that deep and unrestricted BMs can be trained using p-computers generating hundreds of billions of Markov Chain Monte Carlo (MCMC) samples per second, on sparse networks developed originally for use in D-Wave's annealers. To maximize the efficiency of learning the p-computer, we introduce two families of Mean-Field Theory assisted learning algorithms, or xMFTs (x = Naive and Hierarchical). The xMFTs are used to estimate the averages and correlations during the positive phase of the contrastive divergence (CD) algorithm and our custom-designed p-computer is used to estimate the averages and correlations in the negative phase. A custom Field-Programmable-Gate Array (FPGA) emulation of the p-computer architecture takes up to 45 billion flips per second, allowing the implementation of CD-$n$ where $n$ can be of the order of millions, unlike RBMs where $n$ is typically 1 or 2. Experiments on the full MNIST dataset with the combined algorithm show that the positive phase can be efficiently computed by xMFTs without much degradation when the negative phase is computed by the p-computer. Our algorithm can be used in other scalable Ising machines and its variants can be used to train BMs, previously thought to be intractable.