Controlled Forgetting: Targeted Stimulation and Dopaminergic Plasticity Modulation for Unsupervised Lifelong Learning in Spiking Neural Networks

Brain-inspired neural circuit evolution for spiking neural networks

In biological neural systems, different neurons are capable of self-organizing to form different neural circuits for achieving a variety of cognitive functions. However, the current design paradigm of spiking neural networks is based on structures derived from deep learning. Such structures are dominated by feedforward connections without taking into account different types of neurons, which significantly prevent spiking neural networks from realizing their potential on complex tasks. It remains an open challenge to apply the rich dynamical properties of biological neural circuits to model the structure of current spiking neural networks. This paper provides a more biologically plausible evolutionary space by combining feedforward and feedback connections with excitatory and inhibitory neurons. We exploit the local spiking behavior of neurons to adaptively evolve neural circuits such as forward excitation, forward inhibition, feedback inhibition, and lateral inhibition by the local law of spike-timing-dependent plasticity and update the synaptic weights in combination with the global error signals. By using the evolved neural circuits, we construct spiking neural networks for image classification and reinforcement learning tasks. Using the brain-inspired Neural circuit Evolution strategy (NeuEvo) with rich neural circuit types, the evolved spiking neural network greatly enhances capability on perception and reinforcement learning tasks. NeuEvo achieves state-of-the-art performance on CIFAR10, DVS-CIFAR10, DVS-Gesture, and N-Caltech101 datasets and achieves advanced performance on ImageNet. Combined with on-policy and off-policy deep reinforcement learning algorithms, it achieves comparable performance with artificial neural networks. The evolved spiking neural circuits lay the foundation for the evolution of complex networks with functions.

A survey and perspective on neuromorphic continual learning systems

With the advent of low-power neuromorphic computing systems, new possibilities have emerged for deployment in various sectors, like healthcare and transport, that require intelligent autonomous applications. These applications require reliable low-power solutions for sequentially adapting to new relevant data without loss of learning. Neuromorphic systems are inherently inspired by biological neural networks that have the potential to offer an efficient solution toward the feat of continual learning. With increasing attention in this area, we present a first comprehensive review of state-of-the-art neuromorphic continual learning (NCL) paradigms. The significance of our study is multi-fold. We summarize the recent progress and propose a plausible roadmap for developing end-to-end NCL systems. We also attempt to identify the gap between research and the real-world deployment of NCL systems in multiple applications. We do so by assessing the recent contributions in neuromorphic continual learning at multiple levels-applications, algorithms, architectures, and hardware. We discuss the relevance of NCL systems and draw out application-specific requisites. We analyze the biological underpinnings that are used for acquiring high-level performance. At the hardware level, we assess the ability of the current neuromorphic platforms and emerging nano-device-based architectures to support these algorithms in the presence of several constraints. Further, we propose refinements to continual learning metrics for applying them to NCL systems. Finally, the review identifies gaps and possible solutions that are not yet focused upon for deploying application-specific NCL systems in real-life scenarios.

A neuro-inspired computational model of life-long learning and catastrophic interference, mimicking hippocampus novelty-based dopamine modulation and lateral inhibitory plasticity

The human brain has a remarkable lifelong learning capability to acquire new experiences while retaining previously acquired information. Several hypotheses have been proposed to explain this capability, but the underlying mechanisms are still unclear. Here, we propose a neuro-inspired firing-rate computational model involving the hippocampus and surrounding areas, that encompasses two key mechanisms possibly underlying this capability. The first is based on signals encoded by the neuromodulator dopamine, which is released by novel stimuli and enhances plasticity only when needed. The second is based on a homeostatic plasticity mechanism that involves the lateral inhibitory connections of the pyramidal neurons of the hippocampus. These mechanisms tend to protect neurons that have already been heavily employed in encoding previous experiences. The model was tested with images from the MNIST machine learning dataset, and with more naturalistic images, for its ability to mitigate catastrophic interference in lifelong learning. The results show that the proposed biologically grounded mechanisms can effectively enhance the learning of new stimuli while protecting previously acquired knowledge. The proposed mechanisms could be investigated in future empirical animal experiments and inspire machine learning models.

Continuous learning of spiking networks trained with local rules

Artificial neural networks (ANNs) experience catastrophic forgetting (CF) during sequential learning. In contrast, the brain can learn continuously without any signs of catastrophic forgetting. Spiking neural networks (SNNs) are the next generation of ANNs with many features borrowed from biological neural networks. Thus, SNNs potentially promise better resilience to CF. In this paper, we study the susceptibility of SNNs to CF and test several biologically inspired methods for mitigating catastrophic forgetting. SNNs are trained with biologically plausible local training rules based on spike-timing-dependent plasticity (STDP). Local training prohibits the direct use of CF prevention methods based on gradients of a global loss function. We developed and tested the method to determine the importance of synapses (weights) based on stochastic Langevin dynamics without the need for the gradients. Several other methods of catastrophic forgetting prevention adapted from analog neural networks were tested as well. The experiments were performed on freely available datasets in the SpykeTorch environment.

Contributions by metaplasticity to solving the Catastrophic Forgetting Problem

Catastrophic forgetting (CF) refers to the sudden and severe loss of prior information in learning systems when acquiring new information. CF has been an Achilles heel of standard artificial neural networks (ANNs) when learning multiple tasks sequentially. The brain, by contrast, has solved this problem during evolution. Modellers now use a variety of strategies to overcome CF, many of which have parallels to cellular and circuit functions in the brain. One common strategy, based on metaplasticity phenomena, controls the future rate of change at key connections to help retain previously learned information. However, the metaplasticity properties so far used are only a subset of those existing in neurobiology. We propose that as models become more sophisticated, there could be value in drawing on a richer set of metaplasticity rules, especially when promoting continual learning in agents moving about the environment.