Data Science at Home

Episode 61: The 4 best use cases of entropy in machine learning

It all starts from physics. The entropy of an isolated system never decreases… Everyone at school, at some point of his life, learned this in his physics class. What does this have to do with machine learning? To find out, listen to the show.
 
References
Entropy in machine learning https://amethix.com/entropy-in-machine-learning/

Episode 60: Predicting your mouse click (and a crash course in deeplearning)

Deep learning is the future. Get a crash course on deep learning. Now! In this episode I speak to Oliver Zeigermann, author of Deep Learning Crash Course published by Manning Publications at https://www.manning.com/livevideo/deep-learning-crash-course
Oliver (Twitter: @DJCordhose) is a veteran of neural networks and machine learning. In addition to the course - that teaches you concepts from prototype to production - he's working on a really cool project that predicts something people do every day... clicking their mouse. 
If you use promo code poddatascienceathome19 you get a 40% discount for all products on the Manning platform
Enjoy the show!
 
References:
 
Deep Learning Crash Course (Manning Publications)
https://www.manning.com/livevideo/deep-learning-crash-course?a_aid=djcordhose&a_bid=e8e77cbf
 
Companion notebooks for the code samples of the video course "Deep Learning Crash Course"
https://github.com/DJCordhose/deep-learning-crash-course-notebooks/blob/master/README.md
 
Next-button-to-click predictor source code
https://github.com/DJCordhose/ux-by-tfjs
 

Episode 59: How to fool a smart camera with deep learning

In this episode I met three crazy researchers from KULeuven (Belgium) who found a method to fool surveillance cameras and stay hidden just by holding a special t-shirt. We discussed about the technique they used and some consequences of their findings.
They published their paper on Arxiv and made their source code available at https://gitlab.com/EAVISE/adversarial-yolo
Enjoy the show!
 
References
Fooling automated surveillance cameras: adversarial patches to attack person detection Simen Thys, Wiebe Van Ranst, Toon Goedemé
 
Eavise Research Group KULeuven (Belgium)https://iiw.kuleuven.be/onderzoek/eavise

Episode 58: There is physics in deep learning!

There is a connection between gradient descent based optimizers and the dynamics of damped harmonic oscillators. What does that mean? We now have a better theory for optimization algorithms.In this episode I explain how all this works.
All the formulas I mention in the episode can be found in the post The physics of optimization algorithms
Enjoy the show.
 

Episode 57: Neural networks with infinite layers

How are differential equations related to neural networks? What are the benefits of re-thinking neural network as a differential equation engine? In this episode we explain all this and we provide some material that is worth learning. Enjoy the show!
 
Residual Block
 
 
References
[1] K. He, et al., “Deep Residual Learning for Image Recognition”, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 770-778, 2016
[2] S. Hochreiter, et al., “Long short-term memory”, Neural Computation 9(8), pages 1735-1780, 1997.
[3] Q. Liao, et al.,”Bridging the gaps between residual learning, recurrent neural networks and visual cortex”, arXiv preprint, arXiv:1604.03640, 2016.
[4] Y. Lu, et al., “Beyond Finite Layer Neural Networks: Bridging Deep Architectures and Numerical Differential Equation”, Proceedings of the 35th International Conference on Machine Learning (ICML), Stockholm, Sweden, 2018.
[5] T. Q. Chen, et al., ” Neural Ordinary Differential Equations”, Advances in Neural Information Processing Systems 31, pages 6571-6583}, 2018

Episode 56: The graph network

Since the beginning of AI in the 1950s and until the 1980s, symbolic AI approaches have dominated the field. These approaches, also known as expert systems, used mathematical symbols to represent objects and the relationship between them, in order to depict the extensive knowledge bases built by humans. The opposite of the symbolic AI paradigm is named connectionism, which is behind the machine learning approaches of today

Episode 55: Beyond deep learning

The successes that deep learning systems have achieved in the last decade in all kinds of domains are unquestionable. Self-driving cars, skin cancer diagnostics, movie and song recommendations, language translation, automatic video surveillance, digital assistants represent just a few examples of the ongoing revolution that affects or is going to disrupt soon our everyday life.But all that glitters is not gold…Read the full post on the Amethix Technologies blog

Episode 54: Reproducible machine learning

In this episode I speak about how important reproducible machine learning pipelines are. When you are collaborating with diverse teams, several tasks will be distributed among different individuals. Everyone will have good reasons to change parts of your pipeline, leading to confusion and definitely a number of options that soon explode. In all those cases, tracking data and code is extremely helpful to build models that are reproducible anytime, anywhere. Listen to the podcast and learn how.
 

Episode 53: Estimating uncertainty with neural networks

Have you ever wanted to get an estimate of the uncertainty of your neural network? Clearly Bayesian modelling provides a solid framework to estimate uncertainty by design. However, there are many realistic cases in which Bayesian sampling is not really an option and ensemble models can play a role.
In this episode I describe a simple yet effective way to estimate uncertainty, without changing your neural network’s architecture nor your machine learning pipeline at all.
The post with mathematical background and sample source code is published here.

Episode 52: why do machine learning models fail? [RB]

The success of a machine learning model depends on several factors and events. True generalization to data that the model has never seen before is more a chimera than a reality. But under specific conditions a well trained machine learning model can generalize well and perform with testing accuracy that is similar to the one performed during training.
In this episode I explain when and why machine learning models fail from training to testing datasets.