Spike Timing Dependant Plasticity Research Articles

Efficient sparse spiking auto-encoder for reconstruction, denoising and classification

Auto-encoders are capable of performing input reconstruction, denoising, and classification through an encoder-decoder structure. Spiking Auto-Encoders (SAEs) can utilize asynchronous sparse spikes to improve power efficiency and processing latency on neuromorphic hardware. In our work, we propose an efficient SAE trained using only Spike-Timing-Dependant Plasticity (STDP) learning. Our auto-encoder uses the Time-To-First-Spike (TTFS) encoding scheme and needs to update all synaptic weights only once per input, promoting both training and inference efficiency due to the extreme sparsity. We showcase robust reconstruction performance on the Modified National Institute of Standards and Technology (MNIST) and Fashion-MNIST datasets with significantly fewer spikes compared to state-of-the-art SAEs by 1–3 orders of magnitude. Moreover, we achieve robust noise reduction results on the MNIST dataset. When the same noisy inputs are used for classification, accuracy degradation is reduced by 30%–80% compared to prior works. It also exhibits classification accuracies comparable to previous STDP-based classifiers, while remaining competitive with other backpropagation-based spiking classifiers that require global learning through gradients and significantly more spikes for encoding and classification of MNIST/Fashion-MNIST inputs. The presented results demonstrate a promising pathway towards building efficient sparse spiking auto-encoders with local learning, making them highly suited for hardware integration.

Induction of Synaptic Plasticity in Flexible Organic Synaptic Transistors with Cross‐Linked Polymer Dielectric

AbstractControlled cross‐linking of polymer dielectric poly (4‐vinylphenol) (PVP) is demonstrated as an effective tool in enhancing the performance of flexible organic synaptic transistors (OSTs). Investigation of variation of concentration of the cross‐linking agent methylated poly (melamine‐co‐formaldehyde) (PMCF) in PVP in bilayer combination with high‐k hafnium oxide (HfO2) as gate dielectric in devices shows that the lower concentration of cross‐linking agent results in better memory performance. OSTs with 26% PMCF concentration in PVP (by mass) exhibit excellent memory performance with memory window > 4 V for VGS sweep of ±5 V, static retention of ≈104 s, dynamic retention for 500 cycles, and ≈125 continuous program/erase cycles. Pulse paired facilitation with relaxation time constants of 370 and 4670 ms respectively for slow and rapid phases with regulating modulation amplitude of ≈1 resemble a biological synapse. Through excitatory post synaptic current characteristics, spike timing dependant plasticity and spike voltage dependant plasticity are clearly observed, with low energy consumption per spike on the order of 10 pJ. Further, by leveraging the intricate interconnected data transfer and computation phenomenon, “AND” logic is effectively implemented using these OSTs. These exciting results may open up new directions toward the development of hardware for neuromorphic computing.

Spatio-Temporal Sequential Memory Model With Mini-Column Neural Network.

Memory is an intricate process involving various faculties of the brain and is a central component in human cognition. However, the exact mechanism that brings about memory in our brain remains elusive and the performance of the existing memory models is not satisfactory. To overcome these problems, this paper puts forward a brain-inspired spatio-temporal sequential memory model based on spiking neural networks (SNNs). Inspired by the structure of the neocortex, the proposed model is structured by many mini-columns composed of biological spiking neurons. Each mini-column represents one memory item, and the firing of different spiking neurons in the mini-column depends on the context of the previous inputs. The Spike-Timing-Dependant Plasticity (STDP) is used to update the connections between excitatory neurons and formulates association between two memory items. In addition, the inhibitory neurons are employed to prevent incorrect prediction, which contributes to improving the retrieval accuracy. Experimental results demonstrate that the proposed model can effectively store a huge number of data and accurately retrieve them when sufficient context is provided. This work not only provides a new memory model but also suggests how memory could be formulated with excitatory/inhibitory neurons, spike-based encoding, and mini-column structure.

CORDIC-SNN: On-FPGA STDP Learning With Izhikevich Neurons

This paper proposes a neuromorphic platform for on-FPGA online spike timing dependant plasticity (STDP) learning, based on the COordinate Rotation DIgital Computer (CORDIC) algorithms. The implemented platform comprises two main components. First, the Izhikevich neuron model is modified for implementation using the CORDIC algorithm, simulated to ensure the model accuracy, described as hardware, and implemented on FPGA. Second, the STDP learning algorithm is adapted and optimized using the CORDIC method, synthesized for hardware, and implemented to perform on-FPGA online learning on a network of CORDIC Izhikevich neurons to demonstrate competitive Hebbian learning. The implementation results are compared with the original model and state-of-the-art to verify accuracy, effectiveness, and higher speed of the system. These comparisons confirm that the proposed neuromorphic system offers better performance and higher accuracy while being straightforward to implement and suitable to scale.

Recognition of Partially Occluded and Rotated Images With a Network of Spiking Neurons

In this paper, we introduce a novel system for recognition of partially occluded and rotated images. The system is based on a hierarchical network of integrate-and-fire spiking neurons with random synaptic connections and a novel organization process. The network generates integrated output sequences that are used for image classification. The proposed network is shown to provide satisfactory predictive performance given that the number of the recognition neurons and synaptic connections are adjusted to the size of the input image. Comparison of synaptic plasticity activity rule (SAPR) and spike timing dependant plasticity rules, which are used to learn connections between the spiking neurons, indicates that the former gives better results and thus the SAPR rule is used. Test results show that the proposed network performs better than a recognition system based on support vector machines.

Face identification using one spike per neuron: resistance to image degradations

The short response latencies of face selective neurons in the inferotemporal cortex impose major constraints on models of visual processing. It appears that visual information must essentially propagate in a feed-forward fashion with most neurons only having time to fire one spike. We hypothesize that flashed stimuli can be encoded by the order of firing of ganglion cells in the retina and propose a neuronal mechanism, that could be related to fast shunting inhibition, to decode such information. Based on these assumptions, we built a three-layered neural network of retino-topically organized neuronal maps. We showed, by using a learning rule involving spike timing dependant plasticity, that neuronal maps in the output layer can be trained to recognize natural photographs of faces. Not only was the model able to generalize to novel views of the same faces, it was also remarkably resistant to image noise and reductions in contrast.