17 citations · 47 across the 17 of their papers we have counts for
17 papers
Data-Driven Pixel Control: Challenges and Prospects
Saurabh Farkya, Zachary Alan Daniels, Aswin Raghavan +4
Recent advancements in sensors have led to high resolution and high data throughput at the pixel level. Simultaneously, the adoption of increasingly large (deep) neural networks (N…
Improving the Robustness of Quantized Deep Neural Networks to White-Box Attacks using Stochastic Quantization and Information-Theoretic Ensemble Training
Saurabh Farkya, Aswin Raghavan, Avi Ziskind
Most real-world applications that employ deep neural networks (DNNs) quantize them to low precision to reduce the compute needs. We present a method to improve the robustness of qu…
Efficient Model Adaptation for Continual Learning at the Edge
Zachary A. Daniels, Jun Hu, Michael Lomnitz +5
Most machine learning (ML) systems assume stationary and matching data distributions during training and deployment. This is often a false assumption. When ML models are deployed o…
A Domain-Agnostic Approach for Characterization of Lifelong Learning Systems
Megan M. Baker, Alexander New, Mario Aguilar-Simon +44
Despite the advancement of machine learning techniques in recent years, state-of-the-art systems lack robustness to "real world" events, where the input distributions and tasks enc…
System Design for an Integrated Lifelong Reinforcement Learning Agent for Real-Time Strategy Games
Indranil Sur, Zachary Daniels, Abrar Rahman +16
As Artificial and Robotic Systems are increasingly deployed and relied upon for real-world applications, it is important that they exhibit the ability to continually learn and adap…
Low-power In-pixel Computing with Current-modulated Switched Capacitors
David Zhang, Gooitzen van der Wal, Saurabh Farkya +4
We present a scalable in-pixel processing architecture that can reduce the data throughput by 10X and consume less than 30 mW per megapixel at the imager frontend. Unlike the state…