Data Science at Home

Training neural networks faster without GPU [RB] (Ep. 77)

Join the discussion on our Discord server
Training neural networks faster usually involves the usage of powerful GPUs. In this episode I explain an interesting method from a group of researchers from Google Brain, who can train neural networks faster by squeezing the hardware to their needs and making the training pipeline more dense.
Enjoy the show!
 
References
Faster Neural Network Training with Data Echoinghttps://arxiv.org/abs/1907.05550

How to generate very large images with GANs (Ep. 76)

Join the discussion on our Discord server
In this episode I explain how a research group from the University of Lubeck dominated the curse of dimensionality for the generation of large medical images with GANs. The problem is not as trivial as it seems. Many researchers have failed in generating large images with GANs before. One interesting application of such approach is in medicine for the generation of CT and X-ray images.Enjoy the show!
 
References
Multi-scale GANs for Memory-efficient Generation of High Resolution Medical Images https://arxiv.org/abs/1907.01376

[RB] Complex video analysis made easy with Videoflow (Ep. 75)

In this episode I am with Jadiel de Armas, senior software engineer at Disney and author of Videflow, a Python framework that facilitates the quick development of complex video analysis applications and other series-processing based applications in a multiprocessing environment. 
I have inspected the videoflow repo on Github and some of the capabilities of this framework and I must say that it’s really interesting. Jadiel is going to tell us a lot more than what you can read from Github 
 
References
Videflow Github official repository https://github.com/videoflow/videoflow
 

[RB] Validate neural networks without data with Dr. Charles Martin (Ep. 74)

In this episode, I am with Dr. Charles Martin from Calculation Consulting a machine learning and data science consulting company based in San Francisco. We speak about the nuts and bolts of deep neural networks and some impressive findings about the way they work. 
The questions that Charles answers in the show are essentially two:
Why is regularisation in deep learning seemingly quite different than regularisation in other areas on ML?
How can we dominate DNN in a theoretically principled way?
 
References 
The WeightWatcher tool for predicting the accuracy of Deep Neural Networks https://github.com/CalculatedContent/WeightWatcher
Slack channel https://weightwatcherai.slack.com/
Dr. Charles Martin Blog http://calculatedcontent.com and channel https://www.youtube.com/c/calculationconsulting
Implicit Self-Regularization in Deep Neural Networks: Evidence from Random Matrix Theory and Implications for Learning - Charles H. Martin, Michael W. Mahoney

How to cluster tabular data with Markov Clustering (Ep. 73)

In this episode I explain how a community detection algorithm known as Markov clustering can be constructed by combining simple concepts like random walks, graphs, similarity matrix. Moreover, I highlight how one can build a similarity graph and then run a community detection algorithm on such graph to find clusters in tabular data.
You can find a simple hands-on code snippet to play with on the Amethix Blog 
Enjoy the show! 
 
References
[1] S. Fortunato, “Community detection in graphs”, Physics Reports, volume 486, issues 3-5, pages 75-174, February 2010.
[2] Z. Yang, et al., “A Comparative Analysis of Community Detection Algorithms on Artificial Networks”, Scientific Reports volume 6, Article number: 30750 (2016)
[3] S. Dongen, “A cluster algorithm for graphs”, Technical Report, CWI (Centre for Mathematics and Computer Science) Amsterdam, The Netherlands, 2000.
[4] A. J. Enright, et al., “An efficient algorithm for large-scale detection of protein families”, Nucleic Acids Research, volume 30, issue 7, pages 1575-1584, 2002.

Waterfall or Agile? The best methodology for AI and machine learning (Ep. 72)

The two most widely considered software development models in modern project management are, without any doubt, the Waterfall Methodology and the Agile Methodology. In this episode I make a comparison between the two and explain what I believe is the best choice for your machine learning project.
An interesting post to read (mentioned in the episode) is How businesses can scale Artificial Intelligence & Machine Learning https://amethix.com/how-businesses-can-scale-artificial-intelligence-machine-learning/

Training neural networks faster without GPU (Ep. 71)

Training neural networks faster usually involves the usage of powerful GPUs. In this episode I explain an interesting method from a group of researchers from Google Brain, who can train neural networks faster by squeezing the hardware to their needs and making the training pipeline more dense.
Enjoy the show!
 
References
Faster Neural Network Training with Data Echoinghttps://arxiv.org/abs/1907.05550

Validate neural networks without data with Dr. Charles Martin (Ep. 70)

In this episode, I am with Dr. Charles Martin from Calculation Consulting a machine learning and data science consulting company based in San Francisco. We speak about the nuts and bolts of deep neural networks and some impressive findings about the way they work. 
The questions that Charles answers in the show are essentially two:
Why is regularisation in deep learning seemingly quite different than regularisation in other areas on ML?
How can we dominate DNN in a theoretically principled way?
 
References 
The WeightWatcher tool for predicting the accuracy of Deep Neural Networks https://github.com/CalculatedContent/WeightWatcher
Slack channel https://weightwatcherai.slack.com/
Dr. Charles Martin Blog http://calculatedcontent.com and channel https://www.youtube.com/c/calculationconsulting
Implicit Self-Regularization in Deep Neural Networks: Evidence from Random Matrix Theory and Implications for Learning - Charles H. Martin, Michael W. Mahoney
 
 

Complex video analysis made easy with Videoflow (Ep. 69)

In this episode I am with Jadiel de Armas, senior software engineer at Disney and author of Videflow, a Python framework that facilitates the quick development of complex video analysis applications and other series-processing based applications in a multiprocessing environment. 
I have inspected the videoflow repo on Github and some of the capabilities of this framework and I must say that it’s really interesting. Jadiel is going to tell us a lot more than what you can read from Github 
 
References
Videflow Github official repository https://github.com/videoflow/videoflow
 

Episode 68: AI and the future of banking with Chris Skinner [RB]

In this episode I have a wonderful conversation with Chris Skinner.
Chris and I recently got in touch at The banking scene 2019, fintech conference recently held in Brussels. During that conference he talked as a real trouble maker - that’s how he defines himself - saying that “People are not educated with loans, credit, money” and that “Banks are failing at digital”.
After I got my hands on his last book Digital Human, I invited him to the show to ask him a few questions about innovation, regulation and technology in finance.