Search Results for author:
Found 18 papers, 2 papers with code
Dancing along Battery: Enabling Transformer with Run-time Reconfigurability on Mobile Devices
Specifically, RT3 integrates two-level optimizations: First, it utilizes an efficient BP as the first-step compression for resource-constrained mobile devices; then, RT3 heuristically generates a shrunken search space based on the first level optimization and searches multiple pattern sets with diverse sparsity for PP via reinforcement learning to support lightweight software reconfiguration, which corresponds to available frequency levels of DVFS (i. e., hardware reconfiguration).
FGNAS: FPGA-Aware Graph Neural Architecture Search
The success of gragh neural networks (GNNs) in the past years has aroused grow-ing interest and effort in designing best models to handle graph-structured data.
Standing on the Shoulders of Giants: Hardware and Neural Architecture Co-Search with Hot Start
To tackle this issue, HotNAS builds a chain of tools to design hardware to support compression, based on which a global optimizer is developed to automatically co-search all the involved search spaces.
Continual Learning via Online Leverage Score Sampling
In order to mimic the human ability of continual acquisition and transfer of knowledge across various tasks, a learning system needs the capability for continual learning, effectively utilizing the previously acquired skills.
Hardware/Software Co-Exploration of Neural Architectures
We propose a novel hardware and software co-exploration framework for efficient neural architecture search (NAS).
Model-based Deep Reinforcement Learning for Dynamic Portfolio Optimization
Dynamic portfolio optimization is the process of sequentially allocating wealth to a collection of assets in some consecutive trading periods, based on investors' return-risk profile.
Transfer Learning From Synthetic To Real Images Using Variational Autoencoders For Precise Position Detection
Capturing and labeling camera images in the real world is an expensive task, whereas synthesizing labeled images in a simulation environment is easy for collecting large-scale image data.
Internal Model from Observations for Reward Shaping
During reinforcement learning, the agent predicts the reward as a function of the difference between the actual state and the state predicted by the internal model.
Object Detection using Domain Randomization and Generative Adversarial Refinement of Synthetic Images
In this work, we present an application of domain randomization and generative adversarial networks (GAN) to train a near real-time object detector for industrial electric parts, entirely in a simulated environment.
Reward Estimation via State Prediction
We present a novel reward estimation method that is based on a finite sample of optimal state trajectories from expert demon- strations and can be used for guiding an agent to mimic the expert behavior.
Automated flow for compressing convolution neural networks for efficient edge-computation with FPGA
In this paper, we present an automatic flow from trained TensorFlow models to FPGA system on chip implementation of binarized CNN.
Dynamic Boltzmann Machines for Second Order Moments and Generalized Gaussian Distributions
Gaussian DyBM is a DyBM that assumes the predicted data is generated by a Gaussian distribution whose first-order moment (mean) dynamically changes over time but its second-order moment (variance) is fixed.
Conditional generation of multi-modal data using constrained embedding space mapping
We present a conditional generative model that maps low-dimensional embeddings of multiple modalities of data to a common latent space hence extracting semantic relationships between them.
Regularized Dynamic Boltzmann Machine with Delay Pruning for Unsupervised Learning of Temporal Sequences
We introduce Delay Pruning, a simple yet powerful technique to regularize dynamic Boltzmann machines (DyBM).
Distributed Recurrent Neural Forward Models with Synaptic Adaptation for Complex Behaviors of Walking Robots
The locomotive behaviors can consist of a variety of walking patterns along with adaptation that allow the animals to deal with changes in environmental conditions, like uneven terrains, gaps, obstacles etc.
Multiple chaotic central pattern generators with learning for legged locomotion and malfunction compensation
To address this problem, we extend the single chaotic CPG to multiple CPGs with learning.
Cognitive Aging as Interplay between Hebbian Learning and Criticality
In this regard learning in neural networks can serve as a model for the acquisition of skills and knowledge in early development stages i. e. the ageing process and criticality in the network serves as the optimum state of cognitive abilities.
