We featured an instance of Data Driven or Zero Knowledge Sensor Design: a Depth Camera for Close-Range Human Capture and Interaction
This panel video entitled Is Deep Learning the Final Frontier and the End of Signal Processing ? produced a strong reaction from one of the leaders in Deep Learning. His response: Yoshua Bengio's view on Deep Learning. I added a few items in Parallel Paths for Deep Learning and Signal Processing ?. Yoshua Bengio's tutorial slides at KDD that also took place this week are at: Scaling up Deep Learning. Other KDD slides and more can be found here.
In a different direction, we had several genomics items of interest and how compressive sensing and advanced matrix factorization could play a role there:
- Videos and Slides: Next-Generation Sequencing Technologies - Elaine Mardis (2014)
- Improving Pacific Biosciences' Single Molecule Real Time Sequencing Technology through Advanced Matrix Factorization ?
- DNA Sequencing, Information Theory, Advanced Matrix Factorization and all that...
- Saturday Morning Video: Life at the Speed of Light - Craig Venter ( and some remarks )
We also featured quite a few Sunday Morning Insights:
and had at least two entries on reproducible research
We also had quite a few implementations made available by their authors:
- Turbo Compressed Sensing with Partial DFT Sensing Matrix - implementation -
- DDRS : Nonlinear Dimensionality Reduction of Data by Deep Distributed Random Samplings - implementation -
- From Denoising to Compressed Sensing - implementation -
- Optimization of Convex Functions with Random Pursuit - implementation -
- Maximum Entropy Hadamard Sensing of Sparse and Localized Signals - implementation -
- Exponential decay of reconstruction error from binary measurements of sparse signals - implementation -
and one entry related to compressive hardware:
We had several very interesting preprint related entries:
- Universal Streaming
- Compressive Sampling of Polynomial Chaos Expansions: Convergence Analysis and Sampling Strategies
- sFFT-DT: Sparse Fast Fourier Transform for Exactly and Generally K-Sparse Signals by Downsampling and Sparse Recovery
- WiTrack and RTI Goes Wild: Indoor and Outdoor Radio Tomographic Imaging
- The Visual Microphone: Passive Recovery of Sound from Video
- Review: Low Complexity Regularization of Linear Inverse Problems
- The application of Compressed Sensing for Longitudinal MRI / Multichannel Compressive Sensing MRI Using Noiselet Encoding
- Kernel nonnegative matrix factorization without the curse of the pre-image
- Robust width: A characterization of uniformly stable and robust compressed sensing
- A compressed sensing perspective of hippocampal function
- Fastfood: Approximate Kernel Expansions in Loglinear Time - The Paper -
- Foundations of Compressed Sensing
- Compressed beamforming
- Deep Learning and Convolutional Kernel Networks
The blogs
Videos and slides:
- Saturday Morning Video: Life at the Speed of Light - Craig Venter ( and some remarks )
- Videos and Slides: Next-Generation Sequencing Technologies - Elaine Mardis (2014)
- Saturday Morning Videos: Intelligent Machines, Simon Knowles
- Saturday Morning Videos: Two Talks on Synthetic Biology
- Saturday Morning Video: Signal and Image Classification - Stephane Mallat
- Slides: Deep Learning - Russ Salakhutdinov, KDD2014, Accelerating Random Forests on Scikit-Learn - Gilles Louppe
CfP
- #itwist14 and CfP: Biomedical and Astronomical Signal Processing (BASP) Frontiers 2015
- IPAM workshop on Computational Photography and Intelligent Cameras, February 4 - 6, 2015
- TCMM 2014, International Workshop on Technical Computing for Machine Learning and Mathematical Engineering - Last call for participation
Copyright ESA/Rosetta/NAVCAM
Title Comet on 23 August 2014 - NavCam
Released 27/08/2014 10:00 am
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