no code implementations • 3 Mar 2024 • Tousif Rahman, Gang Mao, Sidharth Maheshwari, Rishad Shafik, Alex Yakovlev
System-on-Chip Field-Programmable Gate Arrays (SoC-FPGAs) offer significant throughput gains for machine learning (ML) edge inference applications via the design of co-processor accelerator systems.
no code implementations • 17 Oct 2023 • Bimal Bhattarai, Ole-Christoffer Granmo, Lei Jiao, Per-Arne Andersen, Svein Anders Tunheim, Rishad Shafik, Alex Yakovlev
In brief, the TA of each clause literal has both an absorbing Exclude- and an absorbing Include state, making the learning scheme absorbing instead of ergodic.
no code implementations • 1 Jun 2023 • Samuel Prescott, Adrian Wheeldon, Rishad Shafik, Tousif Rahman, Alex Yakovlev, Ole-Christoffer Granmo
We present use cases for online learning using the proposed infrastructure and demonstrate the energy/performance/accuracy trade-offs.
no code implementations • 22 May 2023 • Omar Ghazal, Simranjeet Singh, Tousif Rahman, Shengqi Yu, Yujin Zheng, Domenico Balsamo, Sachin Patkar, Farhad Merchant, Fei Xia, Alex Yakovlev, Rishad Shafik
Non-volatile memory devices such as Resistive RAM (ReRAM) offer integrated switching and storage capabilities showing promising performance for ML applications.
no code implementations • 19 May 2023 • Rishad Shafik, Tousif Rahman, Adrian Wheeldon, Ole-Christoffer Granmo, Alex Yakovlev
Our analyses provides the first insights into conflicting design tradeoffs involved in energy-efficient and interpretable decision models for this new artificial intelligence hardware architecture.
5 code implementations • 2 Sep 2021 • Adrian Wheeldon, Alex Yakovlev, Rishad Shafik
We present a hardware design for the learning datapath of the Tsetlin machine algorithm, along with a latency analysis of the inference datapath.
no code implementations • 2 Feb 2021 • Dainius Jenkus, Fei Xia, Rishad Shafik, Alex Yakovlev
Then, it is coupled with vertical scaling using transfer Q-learning, which further tunes power/performance based on workload profile using dynamic voltage/frequency scaling (DVFS).
5 code implementations • 7 Dec 2020 • Adrian Wheeldon, Alex Yakovlev, Rishad Shafik, Jordan Morris
Average latency of the proposed circuit is reduced by 10x compared with the synchronous implementation whilst maintaining similar area.
no code implementations • 4 Jul 2020 • K. Darshana Abeyrathna, Ole-Christoffer Granmo, Rishad Shafik, Alex Yakovlev, Adrian Wheeldon, Jie Lei, Morten Goodwin
However, TMs rely heavily on energy-costly random number generation to stochastically guide a team of Tsetlin Automata to a Nash Equilibrium of the TM game.
no code implementations • 15 Oct 2019 • Sergey Mileiko, Thanasin Bunnam, Fei Xia, Rishad Shafik, Alex Yakovlev, Shidhartha Das
We design a PWM-based perceptron which can serve as the fundamental building block for NNs, by using an entirely new method of realising arithmetic in the PWM domain.