SpikeDyn: A Framework for Energy-Efficient Spiking Neural Networks with Continual and Unsupervised Learning Capabilities in Dynamic Environments

The brain uses recurrent spiking neural networks for higher cognitive functions such as symbolic computations, in particular, mathematical computations. We review the current state of research on spike-based symbolic computations of this type. In addition, we present new results which show that surprisingly small spiking neural networks can perform symbolic computations on bit sequences and numbers and even learn such computations using a biologically plausible learning rule. The resulting networks operate in a rather low firing rate regime, where they could not simply emulate artificial neural networks by encoding continuous values through firing rates. Thus, we propose here a new paradigm for symbolic computation in neural networks that provides concrete hypotheses about the organization of symbolic computations in the brain. The employed spike-based network models are the basis for drastically more energy-efficient computer hardware – neuromorphic hardware. Hence, our results can be seen as creating a bridge from symbolic artificial intelligence to energy-efficient implementation in spike-based neuromorphic hardware.

Download Full-text

Deep Convolutional Spiking Neural Networks for Image Classification

10.18122/td.1782.boisestate ◽

2021 ◽

Author(s):

Ruthvik Vaila

Keyword(s):

Neural Network ◽

Neural Networks ◽

Artificial Neural Networks ◽

Gradient Descent ◽

Stochastic Gradient ◽

Spiking Neural Networks ◽

Stochastic Gradient Descent ◽

Data Set ◽

Learning Capabilities ◽

Artificial Neural

Spiking neural networks are biologically plausible counterparts of artificial neural networks. Artificial neural networks are usually trained with stochastic gradient descent (SGD) and spiking neural networks are trained with bioinspired spike timing dependent plasticity (STDP). Spiking networks could potentially help in reducing power usage owing to their binary activations. In this work, we use unsupervised STDP in the feature extraction layers of a neural network with instantaneous neurons to extract meaningful features. The extracted binary feature vectors are then classified using classification layers containing neurons with binary activations. Gradient descent (backpropagation) is used only on the output layer to perform training for classification. Surrogate gradients are proposed to perform backpropagation with binary gradients. The accuracies obtained for MNIST and the balanced EMNIST data set compare favorably with other approaches. The effect of the stochastic gradient descent (SGD) approximations on learning capabilities of our network are also explored. We also studied catastrophic forgetting and its effect on spiking neural networks (SNNs). For the experiments regarding catastrophic forgetting, in the classification sections of the network we use a modified synaptic intelligence that we refer to as cost per synapse metric as a regularizer to immunize the network against catastrophic forgetting in a Single-Incremental-Task scenario (SIT). In catastrophic forgetting experiments, we use MNIST and EMNIST handwritten digits datasets that were divided into five and ten incremental subtasks respectively. We also examine behavior of the spiking neural network and empirically study the effect of various hyperparameters on its learning capabilities using the software tool SPYKEFLOW that we developed. We employ MNIST, EMNIST and NMNIST data sets to produce our results.

Download Full-text

A Supervised Learning Algorithm for Multilayer Spiking Neural Networks Based on Temporal Coding Toward Energy-Efficient VLSI Processor Design

IEEE Transactions on Neural Networks and Learning Systems ◽

10.1109/tnnls.2021.3095068 ◽

2021 ◽

pp. 1-15

Author(s):

Yusuke Sakemi ◽

Kai Morino ◽

Takashi Morie ◽

Kazuyuki Aihara

Keyword(s):

Neural Networks ◽

Supervised Learning ◽

Energy Efficient ◽

Learning Algorithm ◽

Temporal Coding ◽

Spiking Neural Networks ◽

Processor Design

Download Full-text

LogicSNN: A Unified Spiking Neural Networks Logical Operation Paradigm

Electronics ◽

10.3390/electronics10172123 ◽

2021 ◽

Vol 10 (17) ◽

pp. 2123 ◽

Cited By ~ 1

Author(s):

Lingfei Mo ◽

Minghao Wang

Keyword(s):

Machine Learning ◽

Neural Networks ◽

Network Structure ◽

Large Scale ◽

Spike Timing ◽

Spiking Neural Networks ◽

Logical Operation ◽

Large Scale Network ◽

Learning Capabilities ◽

Scale Network

LogicSNN, a unified spiking neural networks (SNN) logical operation paradigm is proposed in this paper. First, we define the logical variables under the semantics of SNN. Then, we design the network structure of this paradigm and use spike-timing-dependent plasticity for training. According to this paradigm, six kinds of basic SNN binary logical operation modules and three kinds of combined logical networks based on these basic modules are implemented. Through these experiments, the rationality, cascading characteristics and the potential of building large-scale network of this paradigm are verified. This study fills in the blanks of the logical operation of SNN and provides a possible way to realize more complex machine learning capabilities.

Download Full-text