All this time, neural networks have had a disadvantage…


"But despite a string of successes, humans just can’t understand how networks built on these MLPs arrive at their conclusions, or whether there may be some underlying principle that explains those results.

"The amazing feats that neural networks perform, like those of a magician, are kept secret, hidden behind what’s commonly called a black box.

"AI researchers have long wondered if it’s possible for a different kind of network to deliver similarly reliable results in a more transparent way.

"An April 2024 study introduced an alternative neural network design, called a Kolmogorov-Arnold network (KAN), that is more transparent yet can also do almost everything a regular neural network can for a certain class of problems. 

"It’s based on a mathematical idea from the mid-20th century that has been rediscovered and reconfigured for deployment in the deep learning era." 


Comments

Popular posts from this blog

Perplexity

Aphorisms: AI

Is this Dalle3 supposed to narrate with images?