Sam Green
YOU?
Author Swipe
View article: Multi-Agent Dynamic Pricing in a Blockchain Protocol Using Gaussian Bandits
Multi-Agent Dynamic Pricing in a Blockchain Protocol Using Gaussian Bandits Open
The Graph Protocol indexes historical blockchain transaction data and makes it available for querying. As the protocol is decentralized, there are many independent Indexers that index and compete with each other for serving queries to the …
View article: Trajectory Planning With Deep Reinforcement Learning in High-Level Action Spaces
Trajectory Planning With Deep Reinforcement Learning in High-Level Action Spaces Open
This paper presents a technique for trajectory planning based on continuously\nparameterized high-level actions (motion primitives) of variable duration. This\ntechnique leverages deep reinforcement learning (Deep RL) to formulate a policy…
View article: Trajectory Planning with Deep Reinforcement Learning in High-Level Action Spaces
Trajectory Planning with Deep Reinforcement Learning in High-Level Action Spaces Open
This paper presents a technique for trajectory planning based on continuously parameterized high-level actions (motion primitives) of variable duration. This technique leverages deep reinforcement learning (Deep RL) to formulate a policy w…
View article: Comparing Neural Accelerators & Neuromorphic Architectures The False Idol of Operations
Comparing Neural Accelerators & Neuromorphic Architectures The False Idol of Operations Open
Accompanying the advanced computing capabilities neural networks are enabling across a suite of application domains, there is a resurgence in interest in understanding what architectures can efficiently enable these advanced computational …
View article: RAPDARTS: Resource-Aware Progressive Differentiable Architecture Search
RAPDARTS: Resource-Aware Progressive Differentiable Architecture Search Open
Early neural network architectures were designed by so-called "grad student descent". Since then, the field of Neural Architecture Search (NAS) has developed with the goal of algorithmically designing architectures tailored for a dataset o…
View article: Neural Inspired Computation Remote Sensing Platform.
Neural Inspired Computation Remote Sensing Platform. Open
Remote sensing (RS) data collection capabilities are rapidly evolving hyper-spectrally (sensing more spectral bands), hyper-temporally (faster sampling rates) and hyper-spatially (increasing number of smaller pixels). Accordingly, sensor t…
View article: Benchmarking Event-Driven Neuromorphic Architectures
Benchmarking Event-Driven Neuromorphic Architectures Open
Neuromorphic architectures are represented by a broad class of hardware, with artificial neural network (ANN) architectures at one extreme and event-driven spiking architectures at another. Algorithms and applications efficiently processed…
View article: Distillation Strategies for Proximal Policy Optimization
Distillation Strategies for Proximal Policy Optimization Open
Vision-based deep reinforcement learning (RL) typically obtains performance benefit by using high capacity and relatively large convolutional neural networks (CNN). However, a large network leads to higher inference costs (power, latency, …
View article: Investigation of the effect of fear and stress on password choice
Investigation of the effect of fear and stress on password choice Open
Background. The current cognitive state, such as cognitive effort and\ndepletion, incidental affect or stress may impact the strength of a chosen\npassword unconsciously. Aim. We investigate the effect of incidental fear and\nstress on the…
View article: Visual Diagnostics for Deep Reinforcement Learning Policy Development
Visual Diagnostics for Deep Reinforcement Learning Policy Development Open
Modern vision-based reinforcement learning techniques often use convolutional neural networks (CNN) as universal function approximators to choose which action to take for a given visual input. Until recently, CNNs have been treated like bl…
View article: Impacts of Mathematical Optimizations on Reinforcement Learning Policy Performance
Impacts of Mathematical Optimizations on Reinforcement Learning Policy Performance Open
Deep neural networks (DNN) now outperform competing methods in many academic and industrial domains. These high-capacity universal function approximators have recently been leveraged by deep reinforcement learning (RL) algorithms to obtain…