New Study: Deep Learning Reaching Computational Limits | A.I & Machine Learning - CDOTrends

Deep learning could soon become technically and economically prohibitive, warns MIT study, as CDOTrends reports.
 

Photo: iStockphoto/anyaberkut

We might be reaching the limits of deep learning, according to a new study (pdf) by researchers at the Massachusetts Institute of Technology (MIT), MIT-IBM Watson AI Lab, Underwood International College, and the University of Brasilia (UnB).

Titled “The computational limits of deep learning”, the study analyzed just over a thousand research 
papers before coming to its conclusion...

While the report conceded that the relationship between performance, model complexity, and computational requirements are not well understood, it noted that deep learning is intrinsically more reliant on computing power than other techniques.

To be clear, the report also noted that the actual computational burden of deep learning models is scaling more rapidly than known theory suggests. If correct, this means that substantial efficiency improvements might be possible.
Read more...

Source: CDOTrends