Abdullahi Ali
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Abdullahi Ali has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
Elgar de Groot
Donders Institute for Brain, Cognition and Behaviour, Radboud University, Nijmegen, The Netherlands
2 shared publications- Tim Christian Kietzmann
Machine Learning Group, Institute for Cognitive Science, Osnabrück University, Osnabrück, Germany
2 shared publications Marcel A. J. van Gerven
Donders Institute for Brain, Cognition and Behaviour, Radboud University, Nijmegen, The Netherlands
1 shared publicationMarcel Antonius Johannes van Gerven
Donders Institute for Brain, Cognition and Behaviour, Radboud University, Nijmegen, The Netherlands
1 shared publicationNasir Ahmad
Donders Institute for Brain, Cognition and Behaviour, Radboud University, Nijmegen, The Netherlands
1 shared publication- Nasir Ahmad
Affiliation Department of Machine Learning and Neural Computing, Donders Institute for Brain, Cognition and Behaviour, Radboud University, Nijmegen, the Netherlands
1 shared publication
Latest Publications
- Open Access
Predictive coding is a consequence of energy efficiency in recurrent neural networks
Predictive coding represents a promising framework for understanding brain function. It postulates that the brain continuously inhibits predictable sensory input, ensuring a preferential processing of surprising elements. A central aspect of this view is its hierarchical connectivity, involving recurrent message passing between excitatory bottom-up signals and inhibitory top-down feedback. Here we use computational modelling to demonstrate that such architectural hard-wiring is not necessary. Rather, predictive coding is shown to emerge as a consequence of energy efficiency. When training recurrent neural networks to minimise their energy consumption while operating in predictive environments, the networks self-organise into prediction and error units with appropriate inhibitory and excitatory interconnections, and learn to inhibit predictable sensory input. Moving beyond the view of purely top-down driven predictions, we furthermore demonstrate, via virtual lesioning experiments, that networks perform predictions on two timescales: fast lateral predictions among sensory units, and slower prediction cycles that integrate evidence over time.
Open AccessPredictive coding is a consequence of energy efficiency in recurrent neural networks
Predictive coding represents a promising framework for understanding brain function. It postulates that the brain continuously inhibits predictable sensory input, ensuring a preferential processing of surprising elements. A central aspect of this view is its hierarchical connectivity, involving recurrent message passing between excitatory bottom-up signals and inhibitory top-down feedback. Here we use computational modelling to demonstrate that such architectural hard-wiring is not necessary. Rather, predictive coding is shown to emerge as a consequence of energy efficiency. When training recurrent neural networks to minimise their energy consumption while operating in predictive environments, the networks self-organise into prediction and error units with appropriate inhibitory and excitatory interconnections, and learn to inhibit predictable sensory input. Moving beyond the view of purely top-down driven predictions, we furthermore demonstrate, via virtual lesioning experiments, that networks perform predictions on two timescales: fast lateral predictions among sensory units, and slower prediction cycles that integrate evidence over time.