Electrical & Computer Engineering, National University of Singapore, Singapore
PhD, Embedded Systems
Thesis: Design Methodologies for Reliable and Energy Efficient Multiprocessor Systems
Electronics & Telecommunication Engineering, Jadavpur University, India
Spike-Based Learning Algorithms
In this project, we are developing biology-inspired algorithms to train spiking neural networks that are deployed in computer vision and bio-signal processing applications.
Neuromorphic Compiler and Run-time
In this project, we are developing the system software to compile and run machine learning codes on many-core neuromorphic hardware.
In this project, we are using hardware-software co-design principles to optimize the software and hardware stacks for neuromorphic systems.
Many-Core Neuromorphic Hardware Development
In this project, we are exploring hardware architectures that mimic the functionality of a human brain and prototype such architectures on FPGA.
I am interested in research that intersects computer architecture and machine learning.
Dependable Neurromorphic Computing
In this project, we are improving the dependability of neuromorphic hardware through software and hardware based optimization techniques.
Title: Real-Time Scheduling of Machine Learning Operations on Heterogeneous Neuromorphic SoC [GitHub Code]
Author: A. Das
Conference: 20th ACM-IEEE International Conference on Formal Methods and Models for System Design (MEMOCODE)
Date: October 13-14, 2022
Title: Built-In Functional Testing of Analog In-Memory Accelerators for Deep Neural Networks
Author: A. Mishra, A. Das and N. Kandasamy
Journal: Electronics, 11, 2592
Date: August, 2022
- DISCO Lab,
- Electrical and Computer Engineering Department,
- Drexel University
- 3101 Market Street, Suite 236,
- Philadelphia, PA 19104, USA