Learning Data Representations:
Beyond Deep Learning - the Magic Theory
Tomaso Poggio

Description

Slides

Slides for this lecture: PDF

Suggested Reading

Anselmi F, J.Z. Leibo, L. Rosasco, J. Mutch, A. Tacchetti, and T. Poggio, "Unsupervised learning of invariant representations with low sample complexity: the magic of sensory cortex or a new framework for machine learning?", CBMM Memo 001, Nov. 2013.

Anselmi F., J.Z. Leibo, L. Rosasco, J. Mutch, A. Tacchetti, and T. Poggio, "Magic Materials: a theory of deep hierarchical architectures for learning sensory representations", CBCL paper, MIT, Cambridge, MA, Apr. 2013.

Anselmi F. and T. Poggio, "Representation learning in sensory cortex: a theory", CBMM Memo 026, Nov. 2014.

---