Talking Machines: Strong AI and autoencoders, with Hugo Larochelle

by Talking Machines

14 September 2015

share this:

image: Engineering at Cambridge/flickr

In episode nineteen we chat with Hugo Larochelle about his work on unsupervised learning, the International Conference on Learning Representations (ICLR), and his teaching style.

His Youtube courses are not to be missed and his twitter feed @Hugo_Larochelle is a great source for paper reviews.

Ryan introduces us to autoencoders (for more, turn to the work of Richard Zemel) plus we tackle the question of what is standing in the way of strong AI.

https://soundcloud.com/talkingmachines/strong-ai-and-autoencoders

Talking Machines is beginning development of season two! We need your help! Donate now on Kickstarter.

tags: AI, neural networks

Talking Machines is your window into the world of machine learning.

AUAI is supported by:

Robot Talk Episode 163 – Robots helping people, with Aaron Edsinger

Robot Talk 25 Sep 2026

In the first episode of Robot Talk season 7, Claire chatted to Aaron Edsinger from Hello Robot about their Stretch robots that can help people with mobility issues live more independently.

An open source approach to physical AI from Intrinsic

Lucy Smith 25 Sep 2026

Find out more about the capabilities of Intrinsic Core.

What’s coming up at #IROS2026?

Lucy Smith 24 Sep 2026

Find out what the International Conference on Intelligent Robots and Systems has in store.

Robotics roadmaps from around the world spotlight of the month: China

IEEE Robotics and Automation Society (RAS) 23 Sep 2026

China is targeting the next industrial revolution by doubling down on embodied AI and humanoid robotics, building directly on its vast manufacturing infrastructure.