|
Towards developmental AI| old_uid | 16773 |
|---|
| title | Towards developmental AI |
|---|
| start_date | 2018/11/21 |
|---|
| schedule | 14h-15h30 |
|---|
| online | no |
|---|
| location_info | amphithéâtre Botté |
|---|
| details | TALC seminar |
|---|
| summary | Even though current machine learning techniques yield systems that achieve parity with humans on several high level tasks, the learning algorithms themselves are orders of magnitude less data efficient than those used by humans, as evidenced by the speed and resilience with which infants learn language and common sense. I review some of our recent attempts to reverse engineer such abilities in the area of unsupervised or weakly supervised learning of speech representations and speech terms, and the learning the laws of intuitive physics by observation of videos. I argue that a triple effort in data collection, algorithm development and fine grained human/machine comparisons is needed to uncover these developmental algorithms. |
|---|
| responsibles | Dutech |
|---|
| |
|