On-chip Few-shot Learning with Surrogate Gradient Descent on a Neuromorphic Processor

Stewart, Kenneth; Orchard, Garrick; Shrestha, Sumit Bam; Neftci, Emre

doi:10.1109/aicas48895.2020.9073948

Cited by 21 publications

(18 citation statements)

References 18 publications

(30 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Much work remains to be done on the spiking algorithm front, but steady progress is being made. Early efforts demonstrate digit recognition, fusion of visual and tactile perception [40], fusion of visual and EMG information [39], persistent attention and tracking [68], and online learning of gestures [102] using event-based sensors interfaced to Loihi.…”

Section: A Event-based Sensing and Perceptionmentioning

confidence: 99%

Advancing Neuromorphic Computing With Loihi: A Survey of Results and Outlook

et al. 2021

Self Cite

View full text Add to dashboard Cite

Deep artificial neural networks apply principles of the brain's information processing that led to breakthroughs in machine learning spanning many problem domains. Neuromorphic computing aims to take this a step further to chips more directly inspired by the form and function of biological neural circuits, so they can process new knowledge, adapt, behave, and learn in real time at low power levels. Despite several decades of research, until recently, very few published results have shown that today's neuromorphic chips can demonstrate quantitative computational value. This is now changing with the advent of Intel's Loihi, a neuromorphic research processor designed to support a broad range of spiking neural networks with sufficient scale, performance, and features to deliver competitive results compared to state-of-the-art contemporary computing architectures. This survey reviews results that are obtained to date with Loihi across the major algorithmic domains under study, including deep learning approaches and novel approaches that aim to more directly harness the key features of spike-based neuromorphic hardware. While conventional feedforward deep neural networks show modest if any benefit on Loihi, more brain-inspired networks using recurrence, precise spike-timing relationships, synaptic plasticity, stochasticity, and sparsity perform certain computation with orders of magnitude lower latency and energy compared to state-of-the-art conventional approaches. These compelling neuromorphic networks solve a diverse range of problems representative of brain-like computation, such as event-based

show abstract

Section: A Event-based Sensing and Perceptionmentioning

confidence: 99%

Advancing Neuromorphic Computing With Loihi: A Survey of Results and Outlook

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…Furthermore, neuromorphic-equipped medical devices will better protect users' sensitive medical data without cloud communication requirements. Moreover, implementation of novel meta learning algorithms, such as few-shot learning, on neuromorphic platforms will enable the rapid adaptation and real-time learning in these systems with a few data points and the least possible computation 39,49 . Example of such applications, where online learning and adaptation of a ML model is crucial, include autonomous driving, surgical robotics, personalized medicine, and precision diagnostic 39,[49][50][51][52] .…”

Section: Discussionmentioning

confidence: 99%

Neuromorphic on-chip recognition of saliva samples of COPD and healthy controls using memristive devices

Zarrin

Zahari

Mahadevaiah

et al. 2020

Sci Rep

View full text Add to dashboard Cite

Chronic Obstructive Pulmonary Disease (COPD) is a life-threatening lung disease, affecting millions of people worldwide. Implementation of Machine Learning (ML) techniques is crucial for the effective management of COPD in home-care environments. However, shortcomings of cloud-based ML tools in terms of data safety and energy efficiency limit their integration with low-power medical devices. To address this, energy efficient neuromorphic platforms can be used for the hardware-based implementation of ML methods. Therefore, a memristive neuromorphic platform is presented in this paper for the on-chip recognition of saliva samples of COPD patients and healthy controls. Results of its performance evaluations showed that the digital neuromorphic chip is capable of recognizing unseen COPD samples with accuracy and sensitivity values of 89% and 86%, respectively. Integration of this technology into personalized healthcare devices will enable the better management of chronic diseases such as COPD.

show abstract

“…Since we present each pattern one after another, the presentation time for N-MNIST is 105 ms, equivalent to the time taken for one saccade in the N-MNIST dataset. For DvsGesture, we take only the first 1,450 ms of the pattern to classify the dataset, as has been done earlier (e.g., Stewart et al, 2020 ) and this is the presentation time. As presynaptic spike rates vary throughout pattern presentation, the output neuron must spike only at the end of the presentation (see Iyer and Basu, 2017 for more details).…”

Section: Spiking Neural Networkmentioning

confidence: 99%

Is Neuromorphic MNIST Neuromorphic? Analyzing the Discriminative Power of Neuromorphic Datasets in the Time Domain

Iyer

Chua

2021

Front. Neurosci.

View full text Add to dashboard Cite

A major characteristic of spiking neural networks (SNNs) over conventional artificial neural networks (ANNs) is their ability to spike, enabling them to use spike timing for coding and efficient computing. In this paper, we assess if neuromorphic datasets recorded from static images are able to evaluate the ability of SNNs to use spike timings in their calculations. We have analyzed N-MNIST, N-Caltech101 and DvsGesture along these lines, but focus our study on N-MNIST. First we evaluate if additional information is encoded in the time domain in a neuromorphic dataset. We show that an ANN trained with backpropagation on frame-based versions of N-MNIST and N-Caltech101 images achieve 99.23 and 78.01% accuracy. These are comparable to the state of the art—showing that an algorithm that purely works on spatial data can classify these datasets. Second we compare N-MNIST and DvsGesture on two STDP algorithms, RD-STDP, that can classify only spatial data, and STDP-tempotron that classifies spatiotemporal data. We demonstrate that RD-STDP performs very well on N-MNIST, while STDP-tempotron performs better on DvsGesture. Since DvsGesture has a temporal dimension, it requires STDP-tempotron, while N-MNIST can be adequately classified by an algorithm that works on spatial data alone. This shows that precise spike timings are not important in N-MNIST. N-MNIST does not, therefore, highlight the ability of SNNs to classify temporal data. The conclusions of this paper open the question—what dataset can evaluate SNN ability to classify temporal data?

show abstract

On-chip Few-shot Learning with Surrogate Gradient Descent on a Neuromorphic Processor

Cited by 21 publications

References 18 publications

Advancing Neuromorphic Computing With Loihi: A Survey of Results and Outlook

Advancing Neuromorphic Computing With Loihi: A Survey of Results and Outlook

Neuromorphic on-chip recognition of saliva samples of COPD and healthy controls using memristive devices

Is Neuromorphic MNIST Neuromorphic? Analyzing the Discriminative Power of Neuromorphic Datasets in the Time Domain

Contact Info

Product

Resources

About