NxTF: An API and Compiler for Deep Spiking Neural Networks on Intel Loihi

@article{Rueckauer2021NxTFAA,
  title={NxTF: An API and Compiler for Deep Spiking Neural Networks on Intel Loihi},
  author={Bodo Rueckauer and Connor Bybee and Ralf Goettsche and Yashwardhan Singh and Joyesh Mishra and Andreas Wild},
  journal={ACM Journal on Emerging Technologies in Computing Systems (JETC)},
  year={2021},
  volume={18},
  pages={1 - 22}
}
Spiking Neural Networks (SNNs) is a promising paradigm for efficient event-driven processing of spatio-temporally sparse data streams. Spiking Neural Networks (SNNs) have inspired the design of and can take advantage of the emerging class of neuromorphic processors like Intel Loihi. These novel hardware architectures expose a variety of constraints that affect firmware, compiler, and algorithm development alike. To enable rapid and flexible development of SNN algorithms on Loihi, we developed… 
View on ACM
arxiv.org
25 Citations
Highly Influential Citations
2
Background Citations
8
Methods Citations
9

25 Citations

Energy-Efficient Deployment of Machine Learning Workloads on Neuromorphic Hardware

Results show that when compared against the Intel Neural Compute Stick 2, Intel's neuromorphic processor, Loihi, consumes up to 27× less power and 5× less energy in the tested image classification tasks by using the SNN improvement techniques.

hxtorch.snn: Machine-learning-inspired Spiking Neural Network Modeling on BrainScaleS-2

This work presents the development of a machine learning-based modeling framework, called hxtorch.snn, that enables the hardware-in-the-loop training of spiking neural networks within PyTorch, including support for auto differentiation in a fully-automated hardware experiment workflow.

DNAsim: Evaluation Framework for Digital Neuromorphic Architectures

This paper introduces a simulation framework that evaluates application mapping on a user-defined NoC-based multi-core digital neuromorphic architecture and evaluates latency and energy based on mapping and abstract spike activity traces which indicate the firing of neurons at specific discrete timesteps defined by the application.

The Backpropagation Algorithm Implemented on Spiking Neuromorphic Hardware

This paper presents a probabilistic procedure for estimating the total number of elements in a proton-proton collisions between two particles and reports the number of particles in a T-4 system.

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

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.

Spiking Neural Operators for Scientific Machine Learning

A SNN-based method to perform regression, which has been a challenge due to the inherent difficulty in representing a function’s input domain and continuous output values as spikes, is presented and a new method for encoding continuous values into spikes based on a triangular matrix is proposed.

Neko: a Library for Exploring Neuromorphic Learning Rules

Neko is an open source Python library that supports PyTorch and TensorFlow backends and can replicate the state-of-the-art algorithms and, in one case, lead to significant outperformance in accuracy and speed.

Temporal Pattern Coding in Deep Spiking Neural Networks

A study of an encoding scheme based on temporal spike patterns that inherits the efficiency of temporal codes but retains the robustness of rate codes and is evaluated on MNIST, CIFAR-10, and ImageNet image classification tasks.

Rectified Linear Postsynaptic Potential Function for Backpropagation in Deep Spiking Neural Networks

The contribution of spike timing dynamics to information encoding, synaptic plasticity and decision making is investigated, providing a new perspective to design of future DeepSNNs and neuromorphic hardware systems.

Spiking Neural Network Integrated Circuits: A Review of Trends and Future Directions

The rapid growth of deep learning, spurred by its successes in various fields ranging from face recognition [1] to game playing [2], has also triggered a growing interest in the design of specialized…

41 References

Event-driven implementation of deep spiking convolutional neural networks for supervised classification using the SpiNNaker neuromorphic platform

Scalable energy-efficient, low-latency implementations of trained spiking Deep Belief Networks on SpiNNaker

A realization of a spike-based variation of previously trained DBNs on the biologically-inspired parallel SpiNNaker platform that achieves a classification performance of 95% on the MNIST handwritten digit dataset, which is only 0.06% less than that of a pure software implementation.

Convolutional networks for fast, energy-efficient neuromorphic computing

This approach allows the algorithmic power of deep learning to be merged with the efficiency of neuromorphic processors, bringing the promise of embedded, intelligent, brain-inspired computing one step closer.

Enabling Deep Spiking Neural Networks with Hybrid Conversion and Spike Timing Dependent Backpropagation

The proposed training methodology converges in less than 20 epochs of spike-based backpropagation for most standard image classification datasets, thereby greatly reducing the training complexity compared to training SNNs from scratch.

An Efficient Spiking Neural Network for Recognizing Gestures with a DVS Camera on the Loihi Neuromorphic Processor

This work trains a DNN for the pre-processed DvsGesture dataset, and converts it into the spike domain for its deployment on Intel Loihi, which enables real-time gesture recognition.

Neuromorphic hardware in the loop: Training a deep spiking network on the BrainScaleS wafer-scale system

This paper demonstrates how iterative training of a hardware-emulated network can compensate for anomalies induced by the analog substrate, and shows that deep spiking networks emulated on analog neuromorphic devices can attain good computational performance despite the inherent variations of the Analog substrate.

Programming Spiking Neural Networks on Intel’s Loihi

The authors present the Loihi toolchain, which consists of an intuitive Python-based API for specifying SNNs, a compiler and runtime for building and executing SNN’s on LoihI, and several target platforms (Loihi silicon, FPGA, and functional simulator).

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

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.

Conversion of Continuous-Valued Deep Networks to Efficient Event-Driven Networks for Image Classification

This paper shows conversion of popular CNN architectures, including VGG-16 and Inception-v3, into SNNs that produce the best results reported to date on MNIST, CIFAR-10 and the challenging ImageNet dataset.

Neuromorphic Nearest Neighbor Search Using Intel's Pohoiki Springs

This work showcases the Pohoiki Springs neuromorphic system, a mesh of 768 interconnected Loihi chips that collectively implement 100 million spiking neurons in silicon, and demonstrates a scalable approximate k-nearest neighbor (k-NN) algorithm for searching large databases that exploits neuromorphic principles.