7 papers · 1 filter
Event-Driven Digital-Time-Domain Inference Architectures for Tsetlin Machines
Tian Lan, Rishad Shafik, Alex Yakovlev
Machine learning fits model parameters to approximate input-output mappings, predicting unknown samples. However, these models often require extensive arithmetic computations durin…
Fast and Compact Tsetlin Machine Inference on CPUs Using Instruction-Level Optimization
Yefan Zeng, Shengyu Duan, Rishad Shafik +1
The Tsetlin Machine (TM) offers high-speed inference on resource-constrained devices such as CPUs. Its logic-driven operations naturally lend themselves to parallel execution on mo…
A Tsetlin Machine Image Classification Accelerator on a Flexible Substrate
Yushu Qin, Marcos L. L. Sartori, Shengyu Duan +3
This paper introduces the first implementation of digital Tsetlin Machines (TMs) on flexible integrated circuit (FlexIC) using Pragmatic's 600nm IGZO-based FlexIC technology. TMs,…
Efficient FPGA Implementation of Time-Domain Popcount for Low-Complexity Machine Learning
Shengyu Duan, Marcos L. L. Sartori, Rishad Shafik +2
Population count (popcount) is a crucial operation for many low-complexity machine learning (ML) algorithms, including Tsetlin Machine (TM)-a promising new ML method, particularly…
Dynamic Tsetlin Machine Accelerators for On-Chip Training at the Edge using FPGAs
Gang Mao, Tousif Rahman, Sidharth Maheshwari +4
The increased demand for data privacy and security in machine learning (ML) applications has put impetus on effective edge training on Internet-of-Things (IoT) nodes. Edge training…
Runtime Tunable Tsetlin Machines for Edge Inference on eFPGAs
Tousif Rahman, Gang Mao, Bob Pattison +5
Embedded Field-Programmable Gate Arrays (eFPGAs) allow for the design of hardware accelerators of edge Machine Learning (ML) applications at a lower power budget compared with trad…