Since the last Nuit Blanche in Review (March 2016) several things happened. First, David MacKay left us. We also had a two implementations featured, a sunday morning insight, several hardware implementations, a suite of preprints showing the continuing great convergence, some in-depth preprints, two Paris Machine Learning meetups, some job positions and more. I note that hardware is becoming important in ML and that the list of preprints falling in The Great Convergence is growing. Enjoy !
Implementations
- A Tutorial on Libra: R package for the Linearized Bregman Algorithm in High Dimensional Statistics - implementation -
- Deep Networks with Stochastic Depth - implementation -
Sunday Morning Insight:
CS Hardware
- Compact all-CMOS spatiotemporal compressive sensing video camera with pixel-wise coded exposure
- Single-Shot Compressive Multiple-Inputs Multiple-Outputs Radar Imaging Using a Two-Port Passive Device
- Time-Resolved Image Demixing
- "The Great Convergence" or How ML/DL is Disrupting Sensor Design
- Exploiting Correlations Among Channels in distributed Compressive Sensing With Convolutional Deep Stacking Networks
- Learning A Deep ℓ∞ Encoder for Hashing
- DeepNano: Deep Recurrent Neural Networks for Base Calling in MinION Nanopore Reads
- Sketching and Neural Networks
- Deep Online Convex Optimization with Gated Games
- Heavy hitters via cluster-preserving clustering
- Bridging the Gaps Between Residual Learning, Recurrent Neural Networks and Visual Cortex / Memory and Information Processing in Recurrent Neural Networks
- Agnostic Estimation of Mean and Covariance
- An information theoretic formulation of the Dictionary Learning and Sparse Coding Problems on Statistical Manifolds
- Fast and Space-optimal Low-rank Factorization in the Streaming Model With Application in Differential Privacy
- Low-rank Solutions of Linear Matrix Equations via Procrustes Flow
- Online Optimization with Costly and Noisy Measurements using Random Fourier Expansions
- Tensor Methods and Recommender Systems / projected fixed-point iteration on a low-rank matrix manifold / "Compress and eliminate" solver for symmetric positive definite sparse matrices
Job:
- CSjob: 2year postdoc, Compressive imaging in Astronomy and Medicine, Heriot-Watt University, Edinburgh, Scotland
- Job: 2-year Postdoc, Institute of Theoretical Physics (IPhT), CEA Saclay, France
Paris Machine Learning meetups
- Paris Machine Learning Meetup #12 Season 3: ML Hardware
- Paris Machine Learning #11 S3: Rogue Waves, Dataiku, eLum, Human Resources, DNN on Matlab, Data and Cars, The Great Convergence
Video:
- Video: Sparse Identification of Nonlinear Dynamics (SINDy)
- Saturday Morning Video: "Can the brain do back-propagation?" - Geoffrey Hinton of Google & University of Toronto
- Wooden blocks and rails - David MacKay ( Information, Inference, and Energy A symposium to celebrate the work of Professor Sir David MacKay FRS)
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.
No comments:
Post a Comment