Search Results for author:
Found 34 papers, 4 papers with code
A Coupled Neural Circuit Design for Guillain-Barre Syndrome
Thus, the resulting coupled analog hardware neuron model can be a proposed model for the simulation of reduced nerve conduction.
Multiscale Voxel Based Decoding For Enhanced Natural Image Reconstruction From Brain Activity
Reconstructing perceived images from human brain activity monitored by functional magnetic resonance imaging (fMRI) is hard, especially for natural images.
Learning in Feedback-driven Recurrent Spiking Neural Networks using full-FORCE Training
However, the presence of a feedback loop from the readout to the recurrent layer de-stabilizes the learning mechanism and prevents it from converging.
A Design Methodology for Fault-Tolerant Computing using Astrocyte Neural Networks
We propose a design methodology to facilitate fault tolerance of deep learning models.
Design-Technology Co-Optimization for NVM-based Neuromorphic Processing Elements
First, on the technology front, we propose an optimization scheme where the NVM resistance state that takes the longest time to sense is set on current paths having the least delay, and vice versa, reducing the average PE latency, which improves the QoS.
Energy-Efficient Respiratory Anomaly Detection in Premature Newborn Infants
We propose a Deep Learning enabled wearable monitoring system for premature newborn infants, where respiratory cessation is predicted using signals that are collected wirelessly from a non-invasive wearable Bellypatch put on infant's body.
Implementing Spiking Neural Networks on Neuromorphic Architectures: A Review
Here, we provide a comprehensive overview of such frameworks proposed for both, platform-based design and hardware-software co-design.
On the Mitigation of Read Disturbances in Neuromorphic Inference Hardware
Our analysis show both a strong dependency on model characteristics such as synaptic activation and criticality, and on the voltage used to read resistance states during inference.
Design of Many-Core Big Little μBrain for Energy-Efficient Embedded Neuromorphic Computing
We propose a system software framework called SentryOS to map SDCNN inference applications to the proposed design.
Design Technology Co-Optimization for Neuromorphic Computing
We present a design-technology tradeoff analysis in implementing machine-learning inference on the processing cores of a Non-Volatile Memory (NVM)-based many-core neuromorphic hardware.
A Design Flow for Mapping Spiking Neural Networks to Many-Core Neuromorphic Hardware
We propose an SDFG-based design flow for mapping spiking neural networks (SNNs) to many-core neuromorphic hardware with the objective of exploring the tradeoff between throughput and buffer size.
DFSynthesizer: Dataflow-based Synthesis of Spiking Neural Networks to Neuromorphic Hardware
We propose DFSynthesizer, an end-to-end framework for synthesizing SNN-based machine learning programs to neuromorphic hardware.
Improving Inference Lifetime of Neuromorphic Systems via Intelligent Synapse Mapping
We propose an architectural solution to extend the read endurance of RRAM-based neuromorphic systems.
Dynamic Reliability Management in Neuromorphic Computing
We propose a new architectural technique to mitigate the aging-related reliability problems in neuromorphic systems, by designing an intelligent run-time manager (NCRTM), which dynamically destresses neuron and synapse circuits in response to the short-term aging in their CMOS transistors during the execution of machine learning workloads, with the objective of meeting a reliability target.
NeuroXplorer 1.0: An Extensible Framework for Architectural Exploration with Spiking Neural Networks
Recently, both industry and academia have proposed many different neuromorphic architectures to execute applications that are designed with Spiking Neural Network (SNN).
On the Role of System Software in Energy Management of Neuromorphic Computing
Based on such formulation, we first evaluate the role of a system software in managing the energy consumption of neuromorphic systems.
Endurance-Aware Mapping of Spiking Neural Networks to Neuromorphic Hardware
We propose eSpine, a novel technique to improve lifetime by incorporating the endurance variation within each crossbar in mapping machine learning workloads, ensuring that synapses with higher activation are always implemented on memristors with higher endurance, and vice versa.
Motif Identification using CNN-based Pairwise Subsequence Alignment Score Prediction
A common problem in bioinformatics is related to identifying gene regulatory regions marked by relatively high frequencies of motifs, or deoxyribonucleic acid sequences that often code for transcription and enhancer proteins.
Compiling Spiking Neural Networks to Mitigate Neuromorphic Hardware Constraints
Spiking Neural Networks (SNNs) are efficient computation models to perform spatio-temporal pattern recognition on {resource}- and {power}-constrained platforms.
Machine learning applications to DNA subsequence and restriction site analysis
Following these preprocessing steps, three different pipelines are proposed to classify subsequences based on their nucleotide sequence and other relevant features corresponding to the restriction sites of over 200 endonucleases.
Thermal-Aware Compilation of Spiking Neural Networks to Neuromorphic Hardware
Such current variations create a thermal gradient within each crossbar of the hardware, depending on the machine learning workload and the mapping of neurons and synapses of the workload to these crossbars.
Reliability-Performance Trade-offs in Neuromorphic Computing
A major source of voltage drop in a crossbar of these architectures are the parasitic components on the crossbar's bitlines and wordlines, which are deliberately made longer to achieve lower cost-per-bit.
Enabling Resource-Aware Mapping of Spiking Neural Networks via Spatial Decomposition
With growing model complexity, mapping Spiking Neural Network (SNN)-based applications to tile-based neuromorphic hardware is becoming increasingly challenging.
A Case for Lifetime Reliability-Aware Neuromorphic Computing
Neuromorphic computing with non-volatile memory (NVM) can significantly improve performance and lower energy consumption of machine learning tasks implemented using spike-based computations and bio-inspired learning algorithms.
Run-time Mapping of Spiking Neural Networks to Neuromorphic Hardware
In this paper, we propose a design methodology to partition and map the neurons and synapses of online learning SNN-based applications to neuromorphic architectures at {run-time}.
Improving Dependability of Neuromorphic Computing With Non-Volatile Memory
We evaluate RENEU using different machine learning applications on a state-of-the-art neuromorphic hardware with NVM synapses.
Compiling Spiking Neural Networks to Neuromorphic Hardware
First, we propose a greedy technique to partition an SNN into clusters of neurons and synapses such that each cluster can fit on to the resources of a crossbar.
PyCARL: A PyNN Interface for Hardware-Software Co-Simulation of Spiking Neural Network
We also use PyCARL to analyze these SNNs for a state-of-the-art neuromorphic hardware and demonstrate a significant performance deviation from software-only simulations.
A Framework to Explore Workload-Specific Performance and Lifetime Trade-offs in Neuromorphic Computing
Our framework first extracts the precise times at which a charge pump in the hardware is activated to support neural computations within a workload.
Mapping Spiking Neural Networks to Neuromorphic Hardware
SpiNePlacer then finds the best placement of local and global synapses on the hardware using a meta-heuristic-based approach to minimize energy consumption and spike latency.
Mapping of Local and Global Synapses on Spiking Neuromorphic Hardware
Partitioning SNNs becomes essential in order to map them on neuromorphic hardware with the major aim to reduce the global communication latency and energy overhead.
Heartbeat Classification in Wearables Using Multi-layer Perceptron and Time-Frequency Joint Distribution of ECG
Heartbeat classification using electrocardiogram (ECG) data is a vital assistive technology for wearable health solutions.
Unsupervised Heart-rate Estimation in Wearables With Liquid States and A Probabilistic Readout
The novelty of our approach lies in (1) encoding spatio-temporal properties of ECG signals directly into spike train and using this to excite recurrently connected spiking neurons in a Liquid State Machine computation model; (2) a novel learning algorithm; and (3) an intelligently designed unsupervised readout based on Fuzzy c-Means clustering of spike responses from a subset of neurons (Liquid states), selected using particle swarm optimization.
Differential Covariance: A New Class of Methods to Estimate Sparse Connectivity from Neural Recordings
In all of our simulated data, the differential covariance-based methods achieved better or similar performance to the GLM method and required fewer data samples.
