Building a New Type of Efficient Artificial Intelligence Inspired by the Brain

We and our partners use cookies to Store and/or access information on a device. We and our partners use data for Personalised ads and content, ad and content measurement, audience insights and product development. An example of data being processed may be a unique identifier stored in a cookie. Some of our partners may process your data as a part of their legitimate business interest without asking for consent. To view the purposes they believe they have legitimate interest for, or to object to this data processing use the vendor list link below. The consent submitted will only be used for data processing originating from this website. If you would like to change your settings or withdraw consent at any time, the link to do so is in our privacy policy accessible from our home page..

Building a New Type of Efficient Artificial Intelligence Inspired by the Brain

Can the brain, limited in its ability to perform precise math, compete with AI systems run on high-speed parallel computers? Yes, for many tasks, as evidenced by everyday experiences. Given this, can a more efficient AI be built based on the brain’s design?

Although the brain’s architecture is very shallow, brain-inspired artificial neural networks’ learning capabilities can outperform deep learning.

Traditionally, artificial intelligence stems from human brain dynamics. However, brain learning is restricted in a number of significant aspects compared to deep learning (DL). First, efficient DL wiring structures (architectures) consist of many tens of feedforward (consecutive) layers, whereas brain dynamics consist of only a few feedforward layers. Second, DL architectures typically consist of many consecutive filter layers, which are essential to identify one of the input classes. If the input is a car, for example, the first filter identifies wheels, the second one identifies doors, the third one lights and after many additional filters it becomes clear that the input object is, indeed, a car. Conversely, brain dynamics contain just a single filter located close to the retina. The last necessary component is the mathematical complex DL training procedure, which is evidently far beyond biological realization.

Scheme of a simple neural network based on dendritic tree (left) vs. a complex artificial intelligence deep learning architecture (right). Credit: Prof. Ido Kanter, Bar-Ilan University

“We’ve shown that efficient learning on an artificial tree architecture, where each weight has a single route to an output unit, can achieve better classification success rates than previously achieved by DL architectures consisting of more layers and filters. This finding paves the way for efficient, biologically-inspired new AI hardware and algorithms,” said Prof. Ido Kanter, of Bar-Ilan’s Department of Physics and Gonda (Goldschmied) Multidisciplinary Brain Research Center, who led the research.

“Highly pruned tree architectures represent a step toward a plausible biological realization of efficient dendritic tree learning by a single or several neurons, with reduced complexity and energy consumption, and biological realization of backpropagation mechanism, which is currently the central technique in AI,” added Yuval Meir, a PhD student and contributor to this work.

The efficient implementation of highly pruned tree training requires a new type of hardware that differs from emerging GPUs that are better fitted to the current DL strategy. The emergence of new hardware is required to efficiently imitate brain dynamics.