Yoshua Bengio on Intelligent Machines
⯀ In an extend interview, Canadian computer scientist Yoshua Bengio on artificial intelligence and how we can create thinking and learning machines through algorithms.
"My main quest is to understand the principles that underlie intelligence, and I believe that this happens through learning."
Yoshua Bengio is a French-born Canadian computer scientist, most noted for his work on artificial neural networks and deep learning. Bengio has been a faculty member at the Université de Montréal since 1993, heads the MILA (Montreal Institute for Learning Algorithms) and is co-director of the Learning in Machines & Brains project of the Canadian Institute for Advanced Research.
Related articles
In a lengthy interview conducted earlier this year, Bengio explains his work, in the field and where it may be headed in the future.
"My main quest is to understand the principles that underlie intelligence, and I believe that this happens through learning—that intelligent behavior arises in nature and in the computers that we are building through learning. The machine, the animal, the human becomes intelligent because it learns," states Bengio in the interview.
According to Bengio, understanding the basic principles is like understanding the laws of aerodynamics when building airplanes.
"We are taking inspiration from brains, we are taking inspiration from a lot of our experiments that we're doing with computers trying to learn from data, we are taking inspiration from other disciplines from physics, from psychology, from neuroscience, and other fields."
According to Bengio, understanding the basic principles is like understanding the laws of aerodynamics when building airplanes.
"We are taking inspiration from brains, we are taking inspiration from a lot of our experiments that we're doing with computers trying to learn from data, we are taking inspiration from other disciplines from physics, from psychology, from neuroscience, and other fields."
Bengio is one of the authors of a leading deep learning textbook, Deep Learning (Adaptive Computation and Machine Learning series)
. Along with Geoff Hinton and Yann LeCun, he was one of the researchers that persevered through the 'AI Winter' to go on to prove that neural networks were a very viable technology. He is also credited for helping to make Montreal a hotbed of AI research.
. Along with Geoff Hinton and Yann LeCun, he was one of the researchers that persevered through the 'AI Winter' to go on to prove that neural networks were a very viable technology. He is also credited for helping to make Montreal a hotbed of AI research.
Comments
Post a Comment
Thank you for your comment!