Building AI from Neuroscience: Bridging the Gap!

Published on June 28, 2023

Imagine you’re baking a cake but you don’t have the recipe. Instead of giving up, you decide to study each ingredient and its properties. That’s exactly what scientists are doing to build artificial intelligence (AI) based on our understanding of the brain! They’re taking a bottom-up approach, analyzing the different features of neurons, synapses, and neural circuits to create a biologically plausible neural network. In this review, researchers discuss recent advances in this exciting field. They explore strategies like optimizing neural networks and incorporating their findings into AI. They even propose a way to categorize neural network classes based on their similarities to biological neural networks. This framework could help guide future research and bridge the gap between neuroscience and AI engineering. Want to learn more? Check out the full article!

Although it may appear infeasible and impractical, building artificial intelligence (AI) using a bottom-up approach based on the understanding of neuroscience is straightforward. The lack of a generalized governing principle for biological neural networks (BNNs) forces us to address this problem by converting piecemeal information on the diverse features of neurons, synapses, and neural circuits into AI. In this review, we described recent attempts to build a biologically plausible neural network by following neuroscientifically similar strategies of neural network optimization or by implanting the outcome of the optimization, such as the properties of single computational units and the characteristics of the network architecture. In addition, we proposed a formalism of the relationship between the set of objectives that neural networks attempt to achieve, and neural network classes categorized by how closely their architectural features resemble those of BNN. This formalism is expected to define the potential roles of top-down and bottom-up approaches for building a biologically plausible neural network and offer a map helping the navigation of the gap between neuroscience and AI engineering.

Read Full Article (External Site)

Leave a Reply

Your email address will not be published. Required fields are marked *

You may use these HTML tags and attributes:

<a href="" title=""> <abbr title=""> <acronym title=""> <b> <blockquote cite=""> <cite> <code> <del datetime=""> <em> <i> <q cite=""> <s> <strike> <strong>