Search Results for author:
Found 17 papers, 0 papers with code
Improving the Robustness of Quantized Deep Neural Networks to White-Box Attacks using Stochastic Quantization and Information-Theoretic Ensemble Training
We present a method to improve the robustness of quantized DNNs to white-box adversarial attacks.
Enhancing Multi-Agent Coordination through Common Operating Picture Integration
Our results demonstrate the efficacy of COP integration, and show that COP-based training leads to robust policies compared to state-of-the-art Multi-Agent Reinforcement Learning (MARL) methods when faced with out-of-distribution initial states.
Efficient Model Adaptation for Continual Learning at the Edge
This paper presents the Encoder-Adaptor-Reconfigurator (EAR) framework for efficient continual learning under domain shifts.
A Domain-Agnostic Approach for Characterization of Lifelong Learning Systems
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 encountered by the deployed systems will not be limited to the original training context, and systems will instead need to adapt to novel distributions and tasks while deployed.
System Design for an Integrated Lifelong Reinforcement Learning Agent for Real-Time Strategy Games
In this paper, we introduce the Lifelong Reinforcement Learning Components Framework (L2RLCF), which standardizes L2RL systems and assimilates different continual learning components (each addressing different aspects of the lifelong learning problem) into a unified system.
Model-Free Generative Replay for Lifelong Reinforcement Learning: Application to Starcraft-2
We present a version of GR for LRL that satisfies two desiderata: (a) Introspective density modelling of the latent representations of policies learned using deep RL, and (b) Model-free end-to-end learning.
Real-time Hyper-Dimensional Reconfiguration at the Edge using Hardware Accelerators
In this paper we present Hyper-Dimensional Reconfigurable Analytics at the Tactical Edge (HyDRATE) using low-SWaP embedded hardware that can perform real-time reconfiguration at the edge leveraging non-MAC (free of floating-point MultiplyACcumulate operations) deep neural nets (DNN) combined with hyperdimensional (HD) computing accelerators.
Lifelong Learning using Eigentasks: Task Separation, Skill Acquisition, and Selective Transfer
We propose a wake-sleep cycle of alternating task learning and knowledge consolidation for learning in our framework, and instantiate it for lifelong supervised learning and lifelong RL.
Lifelong Learning using Eigentasks: Task Separation, Skill Acquisition and Selective Transfer
We propose a wake-sleep cycle of alternating task learning and knowledge consolidation for learning in our framework, and instantiate it for lifelong supervised learning and lifelong RL.
Generative Memory for Lifelong Reinforcement Learning
Our research is focused on understanding and applying biological memory transfers to new AI systems that can fundamentally improve their performance, throughout their fielded lifetime experience.
Generalized Ternary Connect: End-to-End Learning and Compression of Multiplication-Free Deep Neural Networks
The use of deep neural networks in edge computing devices hinges on the balance between accuracy and complexity of computations.
Power-Grid Controller Anomaly Detection with Enhanced Temporal Deep Learning
Specifically, we first train a temporal deep learning model, using only normal HPC readings from legitimate processes that run daily in these power-grid systems, to model the normal behavior of the power-grid controller.
Bit-Regularized Optimization of Neural Nets
Our key idea is to control the expressive power of the network by dynamically quantizing the range and set of values that the parameters can take.
BitNet: Bit-Regularized Deep Neural Networks
The parameters of neural networks are usually unconstrained and have a dynamic range dispersed over all real values.
GPU Activity Prediction using Representation Learning
GPU activity prediction is an important and complex problem.
Low Precision Neural Networks using Subband Decomposition
In this paper, we present a unique approach using lower precision weights for more efficient and faster training phase.
Symbolic Opportunistic Policy Iteration for Factored-Action MDPs
We address the scalability of symbolic planning under uncertainty with factored states and actions.
