A Computational Model Based on Neural Network of Visual Cortex with Conceptors for Image Classification

Li, Xiumin; Yu, Jie; Xu, Wenqiang

doi:10.1007/978-981-16-5188-5_9

Cited by 1 publication

(2 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The population size of MT is 15 × 15 × 8, that of MST is 8 × 8 × 1, and that of the inhibitory group is 8 × 8 × 8. Both MSTd-to-Inh and Inh-to-MSTd connections follow uniform random connectivity with a 0.1 probability [25]. The detailed models for the Izhikevich neuron and synapses are as follows: Here, we use the conductance-based description for synaptic models, which calculates the synaptic current using complex conductance equations for each synaptic receptor type.…”

Section: Foundation Model Of Spiking Neural Networkmentioning

confidence: 99%

“…The correlation coefficient is calculated as: Ā and B are the column-wise mean values of matrices A and B, respectively. A is the test samples from the input data, and B is the product of the MT-to-MST connection weight matrix W and the MST neuronal firing rate matrix H. The ECJ parameters were configured with adjustment ranges as mentioned in [25]. Each iteration evaluated 15 network individuals, and after 100 iterations the best fitness of 72.66% was achieved.…”

Section: Foundation Model Of Spiking Neural Networkmentioning

confidence: 99%

See 1 more Smart Citation

A Visually Inspired Computational Model for Recognition of Optic Flow

Li,

Lin,

et al. 2023

Mathematics

View full text Add to dashboard Cite

Foundation models trained on vast quantities of data have demonstrated impressive performance in capturing complex nonlinear relationships and accurately predicting neuronal responses. Due to the fact that deep learning neural networks depend on massive amounts of data samples and high energy consumption, foundation models based on spiking neural networks (SNNs) have the potential to significantly reduce calculation costs by training on neuromorphic hardware. In this paper, a visually inspired computational model composed of an SNN and echo state network (ESN) is proposed for the recognition of optic flow. The visually inspired SNN model serves as a foundation model that is trained using spike-timing-dependent plasticity (STDP) for extracting core features. The ESN model makes readout decisions for recognition tasks using the linear regression method. The results show that STDP can perform similar functions as non-negative matrix decomposition (NMF), i.e., generating sparse and linear superimposed readouts based on basis flow fields. Once the foundation model is fully trained from enough input samples, it can considerably reduce the training samples required for ESN readout learning. Our proposed SNN-based foundation model facilitates efficient and cost-effective task learning and could also be adapted to new stimuli that are not included in the training of the foundation model. Moreover, compared with the NMF algorithm, the foundation model trained using STDP does not need to be retrained during the testing procedure, contributing to a more efficient computational performance.

show abstract

Section: Foundation Model Of Spiking Neural Networkmentioning

confidence: 99%

Section: Foundation Model Of Spiking Neural Networkmentioning

confidence: 99%