Ryan Dellana
YOU?
Author Swipe
View article: A Domain-Agnostic Approach for Characterization of Lifelong Learning Systems
A Domain-Agnostic Approach for Characterization of Lifelong Learning Systems Open
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…
View article: SEEK: Scoping neuromorphic architecture impact enabling advanced sensing capabilities
SEEK: Scoping neuromorphic architecture impact enabling advanced sensing capabilities Open
Many sensor modalities used for proliferation detection are expanding hyperspectrally, hyperspatially, and hypertemporally. While these assets are often tasked with high-consequence image processing tasks, the significant computational cos…
View article: Biologically Inspired Interception on an Unmanned System
Biologically Inspired Interception on an Unmanned System Open
Borrowing from nature, neural-inspired interception algorithms were implemented onboard a vehicle. To maximize success, work was conducted in parallel within a simulated environment and on physical hardware. The intercept vehicle used only…
View article: Evaluating complexity and resilience trade-offs in emerging memory inference machines.
Evaluating complexity and resilience trade-offs in emerging memory inference machines. Open
DRAM according to their access characteristics, resulting in higher average memory bandwidth and lower average latency. Memory mode provides DRAM-competitive performance with capacity equal to persistent memory. We demonstrate occasional 4…
View article: Low-Power Deep Learning Inference using the SpiNNaker Neuromorphic Platform
Low-Power Deep Learning Inference using the SpiNNaker Neuromorphic Platform Open
n this presentation we will discuss recent results on using the SpiNNaker neuromorphic platform (48-chip model) for deep learning neural network inference. We use the Sandia Labs developed Whet stone spiking deep learning library to train …
View article: Whetstone v.0.9.2
Whetstone v.0.9.2 Open
Whetstone is a deep learning software library for spiking/binary threshold neuromorphic hardware. Built to integrate with Keras models, Whetstone provides a collection of layers, callbacks, and utility functions designed to allow the train…
View article: <em>Mosaics</em>, The Best of Both Worlds: Analog devices with Digital Spiking Communication to build a Hybrid Neural Network Accelerator
<em>Mosaics</em>, The Best of Both Worlds: Analog devices with Digital Spiking Communication to build a Hybrid Neural Network Accelerator Open
Neuromorphic architectures have seen a resurgence of interest in the past decade owing to 100x-1000x efficiency gain over conventional Von Neumann architectures. Digital neuromorphic chips like Intel's Loihi have shown efficiency gains com…
View article: Effective Pruning of Binary Activation Neural Networks
Effective Pruning of Binary Activation Neural Networks Open
Deep learning networks have become a vital tool for image and data processing tasks for deployed and edge applications. Resource constraints, particularly low power budgets, have motivated methods and devices for efficient on-edge inferenc…
View article: Hyperparameter Optimization in Binary Communication Networks for Neuromorphic Deployment
Hyperparameter Optimization in Binary Communication Networks for Neuromorphic Deployment Open
Training neural networks for neuromorphic deployment is non-trivial. There have been a variety of approaches proposed to adapt back-propagation or back-propagation-like algorithms appropriate for training. Considering that these networks o…
View article: Hyperparameter Optimization in Binary Communication Networks for\n Neuromorphic Deployment
Hyperparameter Optimization in Binary Communication Networks for\n Neuromorphic Deployment Open
Training neural networks for neuromorphic deployment is non-trivial. There\nhave been a variety of approaches proposed to adapt back-propagation or\nback-propagation-like algorithms appropriate for training. Considering that\nthese network…
View article: Device-aware inference operations in SONOS nonvolatile memory arrays
Device-aware inference operations in SONOS nonvolatile memory arrays Open
Non-volatile memory arrays can deploy pre-trained neural network models for edge inference. However, these systems are affected by device-level noise and retention issues. Here, we examine damage caused by these effects, introduce a mitiga…
View article: Evaluating complexity and resilience trade-offs in emerging memory inference machines
Evaluating complexity and resilience trade-offs in emerging memory inference machines Open
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 crossba…
View article: Evaluating complexity and resilience trade-offs in emerging memory inference machines
Evaluating complexity and resilience trade-offs in emerging memory inference machines Open
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 crossba…
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: Low-Power Deep Learning Inference using the SpiNNaker Neuromorphic Platform
Low-Power Deep Learning Inference using the SpiNNaker Neuromorphic Platform Open
With the successes deep neural networks have achieved across a range of applications, researchers have been exploring computational architectures to more efficiently execute their operation. In addition to the prevalent role of graphics pr…
View article: Whetstone: A Method for Training Deep Artificial Neural Networks for Binary Communication
Whetstone: A Method for Training Deep Artificial Neural Networks for Binary Communication Open
This paper presents a new technique for training networks for low-precision communication. Targeting minimal communication between nodes not only enables the use of emerging spiking neuromorphic platforms, but may additionally streamline p…