This episode currently has no reviews.
Submit Review- Podcast |
- Brain Inspired
- Publisher |
- Paul Middlebrooks
- Media Type |
- audio
- Podknife tags |
- Artificial Intelligence,
- Data Science,
- Interview,
- Machine Learning,
- Neuroscience,
- Philosophy,
- Psychology,
- Science & Medicine,
- Technology
- Publication Date |
- Sep 02, 2018
- Episode Duration |
- 01:01:48
In this episode, Dan Yamins and I talk about how he uses hierarchical convolutional neural networks to model the ventral visual stream, finding that the units in his model correspond to neurons in progressive layers of the brain. We also delve into the AI agents he develops that learn how to play through intrinsic motivation. Click the episode to get the show notes.
In this episode, Dan Yamins and I talk about how he uses hierarchical convolutional neural networks to model the ventral visual stream, finding that the units in his model correspond to neurons in progressive layers of the brain. We also delve into the AI agents he develops that learn how to play through intrinsic motivation. Click the episode to get the show notes.
Mentioned in the show:
-
The 2 papers we discuss
-
net.org/">ImageNet as one of the most important things to stimulate research in AI, developed by net.org/about-people">these folks.
-
Ventral visual stream (as opposed to the Dorsal stream).
-
Convolutional neural networks were inspired by Kunihiko Fukushima’s Neocognitron
-
2 modern of approaches to solve the ImageNet database:
-
-
Google’s for-large-scale-image.html">NASNet architecture, with about 12 layers
-
Microsoft’s super deep ResNet.
-
-
Object permanence and some video examples
-
The distinction between the intrinsic motivation of Dan and colleagues’ AI agent and the reinforcement learning motivation of the OpenAI 5 team
This episode currently has no reviews.
Submit ReviewThis episode could use a review!
This episode could use a review! Have anything to say about it? Share your thoughts using the button below.
Submit Review