Log In Sign Up

Advantages of biologically-inspired adaptive neural activation in RNNs during learning

by   Victor Geadah, et al.

Dynamic adaptation in single-neuron response plays a fundamental role in neural coding in biological neural networks. Yet, most neural activation functions used in artificial networks are fixed and mostly considered as an inconsequential architecture choice. In this paper, we investigate nonlinear activation function adaptation over the large time scale of learning, and outline its impact on sequential processing in recurrent neural networks. We introduce a novel parametric family of nonlinear activation functions, inspired by input-frequency response curves of biological neurons, which allows interpolation between well-known activation functions such as ReLU and sigmoid. Using simple numerical experiments and tools from dynamical systems and information theory, we study the role of neural activation features in learning dynamics. We find that activation adaptation provides distinct task-specific solutions and in some cases, improves both learning speed and performance. Importantly, we find that optimal activation features emerging from our parametric family are considerably different from typical functions used in the literature, suggesting that exploiting the gap between these usual configurations can help learning. Finally, we outline situations where neural activation adaptation alone may help mitigate changes in input statistics in a given task, suggesting mechanisms for transfer learning optimization.


page 3

page 5

page 7


Activation Functions for Generalized Learning Vector Quantization - A Performance Comparison

An appropriate choice of the activation function (like ReLU, sigmoid or ...

Approximating Activation Functions

ReLU is widely seen as the default choice for activation functions in ne...

Continual Learning of Recurrent Neural Networks by Locally Aligning Distributed Representations

Temporal models based on recurrent neural networks have proven to be qui...

Learning activation functions from data using cubic spline interpolation

Neural networks require a careful design in order to perform properly on...

Deep learning improved by biological activation functions

`Biologically inspired' activation functions, such as the logistic sigmo...

Code Repositories


Nonlinearity modulation and adaptation in artificial RNNs

view repo