Synthesizing Deep Neural Network Architectures using Biological Synaptic Strength Distributions
In this work, we perform an exploratory study on synthesizing deep neural networks using biological synaptic strength distributions, and the potential influence of different distributions on modelling performance particularly for the scenario associated with small data sets. Surprisingly, a CNN with convolutional layer synaptic strengths drawn from biologically-inspired distributions such as log-normal or correlated center-surround distributions performed relatively well suggesting a possibility for designing deep neural network architectures that do not require many data samples to learn, and can sidestep current training procedures while maintaining or boosting modelling performance.
Code (0)
등록된 구현이 없습니다.
Tasks
Small Data Image ClassificationSimilar Papers 제목 키워드 기반
One-to-one Mapping between Stimulus and Neural State: Memory and Classification
Synaptic strength can be seen as probability to propagate impulse, and according to synaptic plasticity, function could exist from propagation activity to synaptic strength. If the function satisfies constraints such as …
General ClassificationLearning in Deep Neural Networks Using a Biologically Inspired Optimizer
Plasticity circuits in the brain are known to be influenced by the distribution of the synaptic weights through the mechanisms of synaptic integration and local regulation of synaptic strength. However, the complex inter…
Locally Learned Synaptic Dropout for Complete Bayesian Inference
The Bayesian brain hypothesis postulates that the brain accurately operates on statistical distributions according to Bayes' theorem. The random failure of presynaptic vesicles to release neurotransmitters may allow the …
Bayesian InferenceRevealing directed effective connectivity of cortical neuronal networks from measurements
In the study of biological networks, one of the major challenges is to understand the relationships between network structure and dynamics. In this paper, we model in vitro cortical neuronal cultures as stochastic dynami…
Functional ConnectivityDiscrete synaptic events induce global oscillations in balanced neural networks
Neural dynamics is triggered by discrete synaptic inputs of finite amplitude. However, the neural response is usually obtained within the diffusion approximation (DA) representing the synaptic inputs as Gaussian noise. W…