<?xml version="1.0" encoding="UTF-8"?><?xml-stylesheet type="text/xsl" href="static/style.xsl"?><OAI-PMH xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/ http://www.openarchives.org/OAI/2.0/OAI-PMH.xsd"><responseDate>2026-11-22T17:38:56Z</responseDate><request verb="GetRecord" identifier="oai:uwspace.uwaterloo.ca:10012/14923" metadataPrefix="dim">https://dspacemainprd01.lib.uwaterloo.ca/server/oai/request</request><GetRecord><record><header><identifier>oai:uwspace.uwaterloo.ca:10012/14923</identifier><datestamp>2025-03-26T23:37:35Z</datestamp><setSpec>com_10012_9900</setSpec><setSpec>com_10012_1</setSpec><setSpec>col_10012_9908</setSpec><setSpec>col_10012_6</setSpec></header><metadata><dim:dim xmlns:dim="http://www.dspace.org/xmlns/dspace/dim" xmlns:doc="http://www.lyncode.com/xoai" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.dspace.org/xmlns/dspace/dim http://www.dspace.org/schema/dim.xsd">
   <dim:field mdschema="dc" element="contributor" qualifier="advisor">Kapre, Nachiket</dim:field>
   <dim:field mdschema="dc" element="contributor" qualifier="author" authority="418e4965-fd88-4ee9-9c21-a220c40c862e" confidence="600">Morcos, Benjamin</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="accessioned">2019-08-22T18:36:43Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="available">2019-08-22T18:36:43Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="issued">2019-08-22</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="submitted">2019-08-09</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="uri">http://hdl.handle.net/10012/14923</dim:field>
   <dim:field mdschema="dc" element="description" qualifier="abstract" lang="en">Low-power, high-speed neural networks are critical for providing deployable embedded AI&#xd;
applications at the edge. We describe a Xilinx FPGA implementation of Neural Engineering&#xd;
Framework (NEF) networks with online learning that outperforms mobile Nvidia GPU&#xd;
implementations by an order of magnitude or more. Specifically, we provide an embedded&#xd;
Python-capable PYNQ FPGA implementation supported with a Xilinx Vivado High-Level&#xd;
Synthesis (HLS) workflow that allows sub-millisecond implementation of adaptive neural&#xd;
networks with low-latency, direct I/O access to the physical world. The outcome of this&#xd;
work is NengoFPGA, a seamless and user-friendly extension to the neural compiler Python&#xd;
package Nengo. To reduce memory requirements and improve performance we tune the&#xd;
precision of the different intermediate variables in the code to achieve competitive absolute&#xd;
accuracy against slower and larger floating-point reference designs. The online learning&#xd;
component of the neural network exploits immediate feedback to adjust the network weights&#xd;
to best support a given arithmetic precision. As the space of possible design configurations&#xd;
of such quantized networks is vast and is subject to a target accuracy constraint, we use&#xd;
the Hyperopt hyper-parameter tuning tool instead of manual search to find Pareto optimal&#xd;
designs. Specifically, we are able to generate the optimized designs in under 500 short&#xd;
iterations of Vivado HLS C synthesis before running the complete Vivado place-and-route&#xd;
phase on that subset, a much longer process not conducive to rapid exploration. For neural&#xd;
network populations of 64–4096 neurons and 1–8 representational dimensions our optimized&#xd;
FPGA implementation generated by Hyperopt has a speedup of 10–484× over a competing&#xd;
cuBLAS implementation on the Jetson TX1 GPU while using 2.4–9.5× less power. Our&#xd;
speedups are a result of HLS-specific reformulation (15× improvement), precision adaptation&#xd;
(3× improvement), and low-latency direct I/O access (1000× improvement).</dim:field>
   <dim:field mdschema="dc" element="language" qualifier="iso" lang="en">en</dim:field>
   <dim:field mdschema="dc" element="publisher" lang="en">University of Waterloo</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en">neural networks</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en">FPGA</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en">nengo</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en">high-level synthesis</dim:field>
   <dim:field mdschema="dc" element="title" lang="en">NengoFPGA: an FPGA Backend for the Nengo Neural Simulator</dim:field>
   <dim:field mdschema="dc" element="type" lang="en">Master Thesis</dim:field>
   <dim:field mdschema="dc" element="pending">false</dim:field>
   <dim:field mdschema="uws-etd" element="degree" qualifier="department" lang="en">Electrical and Computer Engineering</dim:field>
   <dim:field mdschema="uws-etd" element="degree" qualifier="discipline" lang="en">Electrical and Computer Engineering</dim:field>
   <dim:field mdschema="uws-etd" element="degree" qualifier="grantor" lang="en">University of Waterloo</dim:field>
   <dim:field mdschema="uws-etd" element="degree" lang="en">Master of Applied Science</dim:field>
   <dim:field mdschema="uws" element="contributor" qualifier="advisor">Kapre, Nachiket</dim:field>
   <dim:field mdschema="uws" element="contributor" qualifier="affiliation1" lang="en">Faculty of Engineering</dim:field>
   <dim:field mdschema="uws" element="published" qualifier="city" lang="en">Waterloo</dim:field>
   <dim:field mdschema="uws" element="published" qualifier="country" lang="en">Canada</dim:field>
   <dim:field mdschema="uws" element="published" qualifier="province" lang="en">Ontario</dim:field>
   <dim:field mdschema="uws" element="typeOfResource" lang="en">Text</dim:field>
   <dim:field mdschema="uws" element="peerReviewStatus" lang="en">Unreviewed</dim:field>
   <dim:field mdschema="uws" element="scholarLevel" lang="en">Graduate</dim:field>
   <dim:field mdschema="others" element="access-status">open.access</dim:field>
</dim:dim>
</metadata></record></GetRecord></OAI-PMH>