Researchers Slash AI Memory Usage by 90% Without Compromising Performance

Researchers shrink AI memory needs by 90% without breaking a sweat

Deep learning and AI systems are steadily on the rise in terms of usage, thanks to their capability of automating complex computational tasks such as image recognition, computer vision, and natural language processing. However, these systems use billions of parameters and require a gigantic amount of memory usage, which further spikes computational costs. Researchers from Bar-Ilan University have shown a path that allows us to optimize and prune the parameters in these systems without compromising their capabilities. They have demonstrated how understanding the mechanism in deep learning can help prune unnecessary parameters without cutting down on performance.

Less is more: Efficient pruning for reducing AI memory and computational cost

Deep learning and AI systems have made great headway in recent years, especially in their capabilities of automating complex computational tasks such as image recognition, computer vision and natural language processing. Yet, these systems consist of billions of parameters and require great memory usage as well as expensive computational cost. This reality raises the question: Can we optimize, or more correctly, prune, the parameters in those systems without compromising their capabilities? In a study just published in Physical Review E by researchers from Bar-Ilan University, the answer is a resounding yes. In the article, the researchers show how a better understanding of the mechanism underlying successful deep learning leads to an efficient pruning of unnecessary parameters in a deep architecture without affecting its performance. "It all hinges on an initial understanding of what happens in deep networks, how they learn and what parameters are essential to its learning," said Prof. Ido Kanter, of Bar-Ilan's Department of Physics and Gonda (Goldschmied) Multidisciplinary Brain Research Center, who led the research. "It's the ever-present reality of scientific research. The more we know, the better we understand, and in turn, the better and more efficient the technology we can create." "There are many methods that attempt to improve memory and data usage," said Ph.D. student Yarden Tzach, a key contributor to this research. "They were able to improve memory usage and computational complexity, but our method was able to prune up to 90% of the parameters of certain layers, without hindering the system's accuracy at all." These results can lead to better usage of AI systems, both in memory as well as energy consumption. As AI becomes more and more prevalent in our day to day lives, reducing its energy cost will be of utmost importance.