Recent advances at the interface of neuroscience and artificial neural networks
Biological neural networks adapt and learn in diverse behavioral contexts. Artificial neural
networks (ANNs) have exploited biological properties to solve complex problems. However …
networks (ANNs) have exploited biological properties to solve complex problems. However …
On the Effectiveness of Activation Noise in Both Training and Inference for Generative Classifiers
Neurons of the brain never produce the same output twice even when the same stimuli are
presented; this is because of their internal noisy biological processes. Likewise, in this work …
presented; this is because of their internal noisy biological processes. Likewise, in this work …
Long-term stability of neural activity in the motor system
How established behaviors are retained and stably produced by a nervous system in
constant flux remains a mystery. One possible solution is to fix the activity patterns of single …
constant flux remains a mystery. One possible solution is to fix the activity patterns of single …
Efficient interventions in a neural circuit from observations: an information-theoretic study
NA Mehta, P Grover - 2022 IEEE Information Theory Workshop …, 2022 - ieeexplore.ieee.org
Motivated by rapid advances in neuroengineering, we recently proposed an interventional
way of reverse engineering neural circuits that is oriented towards treating disorders. The …
way of reverse engineering neural circuits that is oriented towards treating disorders. The …
[PDF][PDF] Case study 2: A computational complexity perspective on segmentation as a cognitive subcomputation
F Adolfi, T Wareham, I van Rooij - … . bristol. ac. uk, 2023 - research-information.bris.ac.uk
Computational feasibility is a widespread concern that guides the framing and modeling of
natural and artificial intelligence. The specification of cognitive system capacities is often …
natural and artificial intelligence. The specification of cognitive system capacities is often …
Application of the Two-Variable Model to Simulate a Multisensory Reaction-Time Task
To navigate the world in an efficient manner, the brain seamlessly integrates signals
received across multiple sensory modalities. Behavioral studies have suggested that …
received across multiple sensory modalities. Behavioral studies have suggested that …
ON INJECTING NOISE DURING INFERENCE
We study activation noise in a generative energy-based modeling setting during training for
the purpose of regularization. We prove that activation noise is a general form of dropout …
the purpose of regularization. We prove that activation noise is a general form of dropout …