Evaluating complexity and resilience trade-offs in emerging memory inference machines
Neuromorphic-style inference only works well if limited hardware resources are maximized properly, e.g. accuracy continues to scale with parameters and complexity in the face of potential disturbance. In this work, we use realistic crossbar simulations to highlight that compact implementations of deep neural networks are unexpectedly susceptible to collapse from multiple system disturbances. Our work proposes a middle path towards high performance and strong resilience utilizing the Mosaics framework, and specifically by re-using synaptic connections in a recurrent neural network implementation that possesses a natural form of noise-immunity.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Evaluating Supply Chain Resilience During Pandemic Using Agent-based Simulation
Recent pandemics have highlighted vulnerabilities in our global economic systems, especially supply chains. Possible future pandemic raises a dilemma for businesses owners between short-term profitability and long-term s…
Resilience-driven Planning of Electric Power Systems Against Extreme Weather Events
With the increasing frequency of natural disasters, operators must prioritize improvements in the existing electric power grid infrastructure to enhance the resilience of the grid. Resilience to extreme weather events ne…
Resilient Byzantine Agreement with Predictions
This paper studies the Byzantine Agreement problem where the nodes have access to a predictor that flags nodes for suspicion of faulty (Byzantine) behavior. We focus on algorithmic resilience -- the maximum number of fau…
On the Rate-Distortion-Complexity Trade-offs of Neural Video Coding
This paper aims to delve into the rate-distortion-complexity trade-offs of modern neural video coding. Recent years have witnessed much research effort being focused on exploring the full potential of neural video coding…
Model-Free Reinforcement Learning Control for Resilient Cyber-Physical Systems
This paper compares the performance of model-free controllers on a nonlinear system under cyberattacks, including false data injection and denial-of-service attacks. Four RL reward types are analyzed for accuracy, cost, …
Reinforcement Learning