Most neurocomputational models are not hard-wired to perform a task. Instead, they are typically equipped with some kind of learning process. In this post, I'll introduce some notions of how neural networks can learn. Understanding learning processes is important for cognitive neuroscience because they may underly the development of cognitive ability. Let's begin with a …
Category Archives: Computational Modeling
Computational models of cognition in neural systems: WHY?
In my most recent post I gave an overview of the "simple recurrent network" (SRN), but I'd like to take a step back and talk about neuromodeling in general. In particular I'd like to talk about why neuromodeling is going to be instrumental in bringing about the cognitive revolution in neuroscience. A principal goal of …
Continue reading “Computational models of cognition in neural systems: WHY?”
Can a Neural Network be Free…
…from a knee-jerk reaction to its immediate input? Although one of the first things that a Neuroscience student learns about is "reflex reactions" such as the patellar reflex (also known as the knee-jerk reflex), the cognitive neuroscientist is interested in the kind of processing that might occur between inputs and outputs in mappings that are …