Jamal Lottier Molin

About

Jamal Lottier Molin is a researcher at the intersection of machine learning and hardware design, best known for pioneering the use of stochastic computation to implement deep neural networks on FPGAs. His most-cited work (45 citations) introduces a novel architecture for Deep Belief Networks (DBNs) that leverages stochastic bit-streams to dramatically reduce hardware complexity while maintaining high accuracy for character recognition. This breakthrough addresses a critical challenge in deploying DNNs—their computational and power demands—by enabling efficient, hardware-friendly implementations suitable for embedded systems, robotics, and real-time applications. Molin’s contributions have helped bridge the gap between algorithmic advances in deep learning and practical, low-power hardware deployment, influencing subsequent research in stochastic neural computing and FPGA-based accelerators. His work is particularly notable for demonstrating that complex generative models like DBNs can be realized with minimal resources, opening doors for on-device AI in resource-constrained environments. Through this innovative synthesis of machine learning theory and digital design, Molin has established himself as a key figure in the emerging field of efficient deep learning hardware.

Research Focus

Key Achievements

Top Papers

1. 1
   FPGA implementation of a Deep Belief Network architecture for character recognition using stochastic computation

   45 citations · 2015

Key Collaborators

Contact & Links