Chaos-guided Input Structuring for Improved Learning in Recurrent Neural Networks
Anatomical studies demonstrate that brain reformats input information to generate reliable responses for performing computations. However, it remains unclear how neural circuits encode complex spatio-temporal patterns. We show that neural dynamics are strongly influenced by the phase alignment between the input and the spontaneous chaotic activity. Input structuring along the dominant chaotic projections causes the chaotic trajectories to become stable channels (or attractors), hence, improving the computational capability of a recurrent network. Using mean field analysis, we derive the impact of input structuring on the overall stability of attractors formed. Our results indicate that input alignment determines the extent of intrinsic noise suppression and hence, alters the attractor state stability, thereby controlling the network's inference ability.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Suppression of chaos in a partially driven recurrent neural network
The dynamics of recurrent neural networks (RNNs), and particularly their response to inputs, play a critical role in information processing. In many applications of RNNs, only a specific subset of the neurons generally r…
Input correlations impede suppression of chaos and learning in balanced rate networks
Neural circuits exhibit complex activity patterns, both spontaneously and evoked by external stimuli. Information encoding and learning in neural circuits depend on how well time-varying stimuli can control spontaneous n…
Optimal short-term memory before the edge of chaos in driven random recurrent networks
The ability of discrete-time nonlinear recurrent neural networks to store time-varying small input signals is investigated by mean-field theory. The combination of a small input strength and mean-field assumptions makes …
Revisiting chaos in stimulus-driven spiking networks: signal encoding and discrimination
Highly connected recurrent neural networks often produce chaotic dynamics, meaning their precise activity is sensitive to small perturbations. What are the consequences for how such networks encode streams of temporal st…
DecoderHarnessing and modulating chaos to sample from neural generative models
Chaos is generic in strongly-coupled recurrent networks of model neurons, and thought to be an easily accessible dynamical regime in the brain. While neural chaos is typically seen as an impediment to robust computation,…