| Tuning an algorithm for training on unseen data |
| Radio Feature 35: Jurgen Schmidhuber in conversation with Sona Blessing
|
|
|
Tuesday, December 20, 2011
|
|
Jurgen Schmidhuber is Director of the Swiss Artificial Intelligence Lab, is Professor of Artificial Intelligence at the University of Lugano, Switzerland. Amongst his other achievements, he has published more than 250 peer-reviewed scientific papers on topics such as machine learning, financial data prediction, mathematically optimal universal Artificial Intelligence (AI), artificial curiosity and creativity, artificial recurrent neural networks, adaptive robotics, algorithmic information and complexity theory. He shares with us today his thought on AI, in the context of the alternative investment landscape...
Download this feature as MP3 (10.03 MB)
|
|
| |
Listen to the complete feature
Tuning an algorithm for training on unseen data
|
Or listen to selected sub-features
|
-
Q1 - Is it possible to tune an algorithm for training on unseen data?
Duration: 02:26
Play Audio
-
Q2 - Trend toward simplicity? What does "simple" mean?
Duration: 04:19
Play Audio
-
Q3 - Are simpler neural networks more robust?
Duration: 01:19
Play Audio
-
Q4 - Constraints, challenges, developments in implementing such in the field of finance
Duration: 01:11
Play Audio
-
Q5 - Is being faster better?
Duration: 01:40
Play Audio
|