Cory Merkel
YOU?
Author Swipe
View article: Depth-Based Matrix Classification for the HHL Quantum Algorithm
Depth-Based Matrix Classification for the HHL Quantum Algorithm Open
Under the nearing error-corrected era of quantum computing, it is necessary to understand the suitability of certain post-NISQ algorithms for practical problems. One of the most promising, applicable and yet difficult to implement in pract…
View article: Realizing linear synaptic plasticity in electric double layer-gated transistors for improved predictive accuracy and efficiency in neuromorphic computing
Realizing linear synaptic plasticity in electric double layer-gated transistors for improved predictive accuracy and efficiency in neuromorphic computing Open
Neuromorphic computing offers a low-power, parallel alternative to traditional von Neumann architectures by addressing the sequential data processing bottlenecks. Electric double layer-gated transistors (EDLTs) resemble biological synapses…
View article: Realizing Linear Synaptic Plasticity in Electric Double Layer-Gated Transistors for Improved Predictive Accuracy and Efficiency in Neuromorphic Computing
Realizing Linear Synaptic Plasticity in Electric Double Layer-Gated Transistors for Improved Predictive Accuracy and Efficiency in Neuromorphic Computing Open
Neuromorphic computing offers a low-power, parallel alternative to traditional von Neumann architectures by addressing the sequential data processing bottlenecks. Electric double layer-gated transistors (EDLTs) resemble biological synapses…
View article: Contrastive Learning in Memristor-based Neuromorphic Systems
Contrastive Learning in Memristor-based Neuromorphic Systems Open
Spiking neural networks, the third generation of artificial neural networks, have become an important family of neuron-based models that sidestep many of the key limitations facing modern-day backpropagation-trained deep networks, includin…
View article: Poster Session: Eye-tracking while learning greebles.
Poster Session: Eye-tracking while learning greebles. Open
There has been a lot of attention on so-called ‘adversarial images’ that fool machine learning models (MLM). Manipulations to an image or including an unexpected object in a scene can severely disrupt object labeling and parsing by state-o…
View article: NCE focus issue: extreme edge computing
NCE focus issue: extreme edge computing Open
Biological intelligence imparts organisms with the ability to overcome a number of key challenges such as adapting to dynamic environments, learning from experience, and making complex decisions, even within a daunting set of constraints (…
View article: Synaptic Scaling and Optimal Bias Adjustments for Power Reduction in Neuromorphic Systems
Synaptic Scaling and Optimal Bias Adjustments for Power Reduction in Neuromorphic Systems Open
Recent animal studies have shown that biological brains can enter a low power mode in times of food scarcity. This paper explores the possibility of applying similar mechanisms to a broad class of neuromorphic systems where power consumpti…
View article: Exploiting Logic Locking for a Neural Trojan Attack on Machine Learning Accelerators
Exploiting Logic Locking for a Neural Trojan Attack on Machine Learning Accelerators Open
Logic locking has been proposed to safeguard intellectual property (IP) during chip fabrication. Logic locking techniques protect hardware IP by making a subset of combinational modules in a design dependent on a secret key that is withhel…
View article: Energy-efficient and noise-tolerant neuromorphic computing based on memristors and domino logic
Energy-efficient and noise-tolerant neuromorphic computing based on memristors and domino logic Open
The growing scale and complexity of artificial intelligence (AI) models has prompted several new research efforts in the area of neuromorphic computing. A key aim of neuromorphic computing is to enable advanced AI algorithms to run on ener…
View article: Circuit Optimization Techniques for Efficient Ex-Situ Training of Robust Memristor Based Liquid State Machine
Circuit Optimization Techniques for Efficient Ex-Situ Training of Robust Memristor Based Liquid State Machine Open
Spiking neural network hardware offers a high performance, power-efficient and robust platform for the processing of complex data. Many of these systems require supervised learning, which poses a challenge when using gradient-based algorit…
View article: Accelerating the training of single-layer binary neural networks using the HHL quantum algorithm
Accelerating the training of single-layer binary neural networks using the HHL quantum algorithm Open
Binary Neural Networks are a promising technique for implementing efficient deep models with reduced storage and computational requirements. The training of these is however, still a compute-intensive problem that grows drastically with th…
View article: Enhancing Adversarial Attacks on Single-Layer NVM Crossbar-Based Neural Networks with Power Consumption Information
Enhancing Adversarial Attacks on Single-Layer NVM Crossbar-Based Neural Networks with Power Consumption Information Open
Adversarial attacks on state-of-the-art machine learning models pose a significant threat to the safety and security of mission-critical autonomous systems. This paper considers the additional vulnerability of machine learning models when …
View article: Effect of biologically-motivated energy constraints on liquid state machine dynamics and classification performance
Effect of biologically-motivated energy constraints on liquid state machine dynamics and classification performance Open
Equipping edge devices with intelligent behavior opens up new possibilities for automating the decision making in extreme size, weight, and power-constrained application domains. To this end, several recent lines of research are aimed at t…
View article: On the Adversarial Robustness of Quantized Neural Networks
On the Adversarial Robustness of Quantized Neural Networks Open
Reducing the size of neural network models is a critical step in moving AI from a cloud-centric to an edge-centric (i.e. on-device) compute paradigm. This shift from cloud to edge is motivated by a number of factors including reduced laten…
View article: Model Extraction and Adversarial Attacks on Neural Networks using Switching Power Information
Model Extraction and Adversarial Attacks on Neural Networks using Switching Power Information Open
Artificial neural networks (ANNs) have gained significant popularity in the last decade for solving narrow AI problems in domains such as healthcare, transportation, and defense. As ANNs become more ubiquitous, it is imperative to understa…
View article: Exploring Energy-Accuracy Tradeoffs in AI Hardware
Exploring Energy-Accuracy Tradeoffs in AI Hardware Open
Artificial intelligence (AI) is playing an increasingly significant role in our everyday lives. This trend is expected to continue, especially with recent pushes to move more AI to the edge. However, one of the biggest challenges associate…
View article: Energy Constraints Improve Liquid State Machine Performance
Energy Constraints Improve Liquid State Machine Performance Open
A model of metabolic energy constraints is applied to a liquid state machine in order to analyze its effects on network performance. It was found that, in certain combinations of energy constraints, a significant increase in testing accura…
View article: A Segmented Attractor Network for Neuromorphic Associative Learning
A Segmented Attractor Network for Neuromorphic Associative Learning Open
This work describes a segmented attractor network that records memories across different sets of information. Unlike typical attractor networks that can associate any given inputs with one another, the attractor network presented here trac…
View article: A Low-Power Domino Logic Architecture for Memristor-Based Neuromorphic Computing
A Low-Power Domino Logic Architecture for Memristor-Based Neuromorphic Computing Open
We propose a domino logic architecture for memristor-based neuromorphic computing. The design uses the delay of memristor RC circuits to represent synaptic computations and a simple binary neuron activation function. Synchronization scheme…
View article: A Low-Power Domino Logic Architecture for Memristor-Based Neuromorphic\n Computing
A Low-Power Domino Logic Architecture for Memristor-Based Neuromorphic\n Computing Open
We propose a domino logic architecture for memristor-based neuromorphic\ncomputing. The design uses the delay of memristor RC circuits to represent\nsynaptic computations and a simple binary neuron activation function.\nSynchronization sch…
View article: An FPGA Implementation of a Time Delay Reservoir Using Stochastic Logic
An FPGA Implementation of a Time Delay Reservoir Using Stochastic Logic Open
This article presents and demonstrates a stochastic logic time delay reservoir design in FPGA hardware. The reservoir network approach is analyzed using a number of metrics, such as kernel quality, generalization rank, and performance on s…
View article: Current-mode Memristor Crossbars for Neuromemristive Systems
Current-mode Memristor Crossbars for Neuromemristive Systems Open
Motivated by advantages of current-mode design, this brief contribution explores the implementation of weight matrices in neuromemristive systems via current-mode memristor crossbar circuits. After deriving theoretical results for the rang…
View article: Design of a time delay reservoir using stochastic logic: A feasibility study
Design of a time delay reservoir using stochastic logic: A feasibility study Open
This paper presents a stochastic logic time delay reservoir design. The reservoir is analyzed using a number of metrics, such as kernel quality, generalization rank, performance on simple benchmarks, and is also compared to a deterministic…
View article: A design of HTM spatial pooler for face recognition using memristor-CMOS hybrid circuits
A design of HTM spatial pooler for face recognition using memristor-CMOS hybrid circuits Open
Hierarchical Temporal Memory (HTM) is a machine learning algorithm that is inspired from the working principles of the neocortex, capable of learning, inference, and prediction for bit-encoded inputs. Spatial pooler is an integral part of …
View article: Design and Analysis of a Neuromemristive Reservoir Computing Architecture for Biosignal Processing
Design and Analysis of a Neuromemristive Reservoir Computing Architecture for Biosignal Processing Open
Reservoir computing (RC) is gaining traction in several signal processing domains, owing to its non-linear stateful computation, spatiotemporal encoding, and reduced training complexity over recurrent neural networks (RNNs). Previous studi…