I meant to post this yesterday. Oh well.
Nando de Freitas is currently teaching a course at Oxford on Machine Learning and it is videotaped:
- Deep learning at Oxford 2015
- Deep learning - Introduction
- Deep learning - linear models
- Deep learning - maximum likelihood and information
- Deep learning - regularization, model complexity and data complexity (part 1)
- Deep learning - Optimization
- Deep learning - Deep learning - regularization, model complexity and data complexity (part 1)
All the slides should be here.
I also found this series of ICLR videos from last year:
- ICLR14: J Bruna: Spectral Networks and Locally Connected Networks on Graphs
- ICLR14: J Masci: Sparse similarity-preserving hashing
- ICLR14: P Sprechmann (for Qiang Qiu): Learning Transformations for Classification Forests
- ICLR14: P Sermanet: OverFeat: Integrated Recognition, Localization and Detection using ConvNets
- ICLR14: D Kingma: Auto-Encoding Variational Bayes
- ICLR14: A Klami: Group-sparse Embeddings in Collective Matrix Factorization
- ICLR14 Invited Talk: Vincent Vanhoucke: "Learning visual representations at scale"
- ICLR14 Workshop: S Wang: Relaxations for inference in RBM
- ICLR14 Workshop: A Modi: Learning Semantic Script Knowledge with Event Embeddings
- ICLR14 Workshop: A Szlam: Unsupervised Feature Learning by Deep Sparse Coding
- ICLR14: M Norouzi: Zero-Shot Learning by Convex Combination...
- ICLR14 Invited Talk: Hynek Hermansky "Speech representations: 'knowledge' or data?"
- ICLR14: A Saxe: Exact solutions to the nonlinear dynamics of learning...
- ICLR14: T Schaul: Unit Tests for Stochastic Optimization
- ICLR14: R Pascanu: Revisiting Natural Gradient for Deep Networks
- ICLR14 Invited talk: Rich Sutton "Myths of Representation Learning".
Liked this entry ? subscribe to Nuit Blanche's feed, there's more where that came from. You can also subscribe to Nuit Blanche by Email, explore the Big Picture in Compressive Sensing or the Matrix Factorization Jungle and join the conversations on compressive sensing, advanced matrix factorization and calibration issues on Linkedin.