Khaleelulla Khan Nazeer
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Khaleelulla Khan Nazeer has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
Anand Subramoney
Dept. of Computer Science Royal Holloway University of London Egham United Kingdom
1 shared publicationBernhard Vogginger
And Neuro-Microelectronics Chair of Highly-Parallel VLSI-Systems Technische Universität Dresden Germany
1 shared publicationChristian Mayr
And Neuro-Microelectronics Chair of Highly-Parallel VLSI-Systems Technische Universität Dresden Germany
1 shared publicationDavid Kappel
Institut für Neuroinformatik Ruhr Universität Bochum Bochum Germany
1 shared publicationMark Schöne
And Neuro-Microelectronics Chair of Highly-Parallel VLSI-Systems Technische Universität Dresden Germany
1 shared publicationRishav Mukherji
Birla Institute of Technology and Science Pilani -Goa Campus Goa India
1 shared publication
Latest Publications
- Open Access
Language Modeling on a SpiNNaker 2 Neuromorphic Chip
As large language models continue to scale in size rapidly, so too does the computational power required to run them. Event-based networks on neuromorphic devices offer a potential way to reduce energy consumption for inference significantly. However, to date, most event-based networks that can run on neuromorphic hardware, including spiking neural networks (SNNs), have not achieved task performance even on par with LSTM models for language modeling. As a result, language modeling on neuromorphic devices has seemed a distant prospect. In this work, we demonstrate the first-ever implementation of a language model on a neuromorphic device - specifically the SpiNNaker 2 chip - based on a recently published event-based architecture called the EGRU. SpiNNaker 2 is a many-core neuromorphic chip designed for large-scale asynchronous processing, while the EGRU is architected to leverage such hardware efficiently while maintaining competitive task performance. This implementation marks the first time a neuromorphic language model matches LSTMs, setting the stage for taking task performance to the level of large language models. We also demonstrate results on a gesture recognition task based on inputs from a DVS camera. Overall, our results showcase the feasibility of this neuro-inspired neural network in hardware, highlighting significant gains versus conventional hardware in energy efficiency for the common use case of single batch inference.
Open AccessLanguage Modeling on a SpiNNaker 2 Neuromorphic Chip
As large language models continue to scale in size rapidly, so too does the computational power required to run them. Event-based networks on neuromorphic devices offer a potential way to reduce energy consumption for inference significantly. However, to date, most event-based networks that can run on neuromorphic hardware, including spiking neural networks (SNNs), have not achieved task performance even on par with LSTM models for language modeling. As a result, language modeling on neuromorphic devices has seemed a distant prospect. In this work, we demonstrate the first-ever implementation of a language model on a neuromorphic device - specifically the SpiNNaker 2 chip - based on a recently published event-based architecture called the EGRU. SpiNNaker 2 is a many-core neuromorphic chip designed for large-scale asynchronous processing, while the EGRU is architected to leverage such hardware efficiently while maintaining competitive task performance. This implementation marks the first time a neuromorphic language model matches LSTMs, setting the stage for taking task performance to the level of large language models. We also demonstrate results on a gesture recognition task based on inputs from a DVS camera. Overall, our results showcase the feasibility of this neuro-inspired neural network in hardware, highlighting significant gains versus conventional hardware in energy efficiency for the common use case of single batch inference.