Skip to content
TLexDR
YB
Guest dossier

Yoshua Bengio

artificial intelligence researcherprofessorcomputer scientistinformation scientist
1 appearance ·5 ideas explored ·Wikipedia ·✓ verified

Yoshua Bengio is a Canadian computer scientist, and a pioneer of artificial neural networks and deep learning. He is a professor at the Université de Montréal and co-president and scientific director of the nonprofit LawZero. He founded Mila, the Quebec Artificial Intelligence (AI) Institute, and was its scientific director until 2025.

Across 1 conversation, Yoshua Bengio ranges across generalization, training_objectives, AI safety. Yoshua Bengio argues that neural networks struggle with credit assignment over long durations, unlike biological systems. Bengio believes that increasing neural network depth won't solve representational issues; new training objectives are needed.

Synthesized by TLexDR from 1 conversation. AI-generated. Report an inaccuracy

For the specialist
preview
Bengio highlights that current neural networks' inability to perform credit assignment over long time spans limits their learning capabilities.
Yoshua Bengio: Deep Learning
He emphasizes the need for new training objectives over simply increasing neural network depth to address representational issues.
Yoshua Bengio: Deep Learning
The appearance

Every conversation, in order

Reading list

What they pointed you toward

videos

Ex Machina
by Alex Garland
Every idea, by region

The full territory

Adjacent minds

Others exploring the same ideas