Data Science at Home

In this episode I explain a very effective technique that allows one to infer the membership of any record at hand to the (private) training dataset used to train the target model. The effectiveness of such technique is due to the fact that it works on black-box models of which there is no access to the data used for training, nor model parameters and hyperparameters. Such a scenario is very reali...

Masking, obfuscating, stripping, shuffling. All the above techniques try to do one simple thing: keeping the data private while sharing it with third parties. Unfortunately, they are not the silver bullet to confidentiality. All the players in the synthetic data space rely on simplistic techniques that are not secure, might not be compliant and risky for production. At pryml we do things different...

There are very good reasons why a financial institution should never share their data. Actually, they should never even move their data. Ever. In this episode I explain you why.     This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit datascienceathome.substack.com

Building reproducible models is essential for all those scenarios in which the lead developer is collaborating with other team members. Reproducibility in machine learning shall not be an art, rather it should be achieved via a methodical approach. In this episode I give a few suggestions about how to make your ML models reproducible and keep your workflow as smooth. Enjoy the show! Come visit us...

Data science and data engineering are usually two different departments in organisations. Bridging the gap between the two is essential to success. Many times the brilliant applications created by data scientists don't find a match in production, just because they are not production-ready. In this episode I have a talk with Daan Gerits, co-founder and CTO at Pryml.io   This is a public episode. If...

Why so much silence? Building a company! That's why :) I am building pryml , a platform that allows data scientists build their applications on data they cannot get access to. This is the first of a series of episodes in which I will speak about the technology and the challenges we are facing while we build it.  Happy listening and stay tuned! This is a public episode. If you would like to discuss...

In the last episode of 2019 I speak with Filip Piekniewski  about some of the most worth noting findings in AI and machine learning in 2019. As a matter of fact, the entire field of AI has been inflated by hype and claims that are hard to believe. A lot of the promises made a few years ago have revealed quite hard to achieve, if not impossible. Let's stay grounded and realistic on the potential of...

  This is the fourth and last episode of mini series "The dark side of AI". I am your host Francesco and I’m with Chiara Tonini from London. The title of today’s episode is Bias in the machine      C: Francesco, today we are starting with an infuriating discussion. Are you ready to be angry?    F: yeah sure is this about brexit? No, I don’t talk about that. In 1986 the New York City’s Rockefeller...

Get in touch with us Join the discussion about data science, machine learning and artificial intelligence on our Discord server   Episode transcript We always hear the word “metadata”, usually in a sentence that goes like this   Your Honor, I swear, we were not collecting users data, just metadata.   Usually the guy saying this sentence is Zuckerberg, but could be anybody from Amazon or Google. “J...

In 2017 a research group at the University of Washington did a study on the Black Lives Matter movement on Twitter. They constructed what they call a “shared audience graph” to analyse the different groups of audiences participating in the debate, and found an alignment of the groups with the political left and political right, as well as clear alignments with groups participating in other debates...

Chamath Palihapitiya, former Vice President of User Growth at Facebook, was giving a talk at Stanford University, when he said this: “I feel tremendous guilt. The short-term, dopamine-driven feedback loops that we have created are destroying how society works ”. He was referring to how social media platforms leverage our neurological build-up in the same way slot machines and cocaine do, to keep u...

Some of the most powerful NLP models like BERT and GPT-2 have one thing in common: they all use the transformer architecture. Such architecture is built on top of another important concept already known to the community: self-attention. In this episode I explain what these mechanisms are, how they work and why they are so powerful. Don't forget to subscribe to our Newsletter  or join the discussio...

Generative Adversarial Networks or GANs are very powerful tools to generate data. However, training a GAN is not easy. More specifically, GANs suffer of three major issues such as instability of the training procedure, mode collapse and vanishing gradients.   In this episode I not only explain the most challenging issues one would encounter while designing and training Generative Adversarial Netwo...

What happens to a neural network trained with random data? Are massive neural networks just lookup tables or do they truly learn something?  Today’s episode will be about memorisation and generalisation in deep learning, with Stanislaw Jastrzębski from New York University. Stan spent two summers as a visiting student with Prof. Yoshua Bengio  and has been working on  Understanding and improving ho...

In this episode I speak with Jon Krohn, author of Deeplearning Illustrated  a book that makes deep learning easier to grasp.  We also talk about some important guidelines to take into account whenever you implement a deep learning model, how to deal with bias in machine learning used to match jobs to candidates and the future of AI.      You can purchase the book from  informit.com/dsathome  with...

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 gene...

Some of the most powerful NLP models like BERT and GPT-2 have one thing in common: they all use the transformer architecture. Such architecture is built on top of another important concept already known to the community: self-attention. In this episode I explain what these mechanisms are, how they work and why they are so powerful. Don't forget to subscribe to our Newsletter  or join the discussio...

Join the discussion on our Discord server   In this episode, I am with Aaron Gokaslan , computer vision researcher, AI Resident at Facebook AI Research. Aaron is the author of OpenGPT-2, a parallel NLP model to the most discussed version that OpenAI decided not to release because too accurate to be published. We discuss about image-to-image translation, the dangers of the GPT-2 model and the futur...

Join the discussion on our Discord server   After reinforcement learning agents doing great at playing Atari video games, Alpha Go, doing financial trading, dealing with language modeling, let me tell you the real story here. In this episode I want to shine some light on reinforcement learning (RL) and the limitations that every practitioner should consider before taking certain directions. RL see...

Join the discussion on our Discord server   In this episode I have an amazing conversation with Jimmy Soni and Rob Goodman, authors of “A mind at play”, a book entirely dedicated to the life and achievements of Claude Shannon. Claude Shannon does not need any introduction. But for those who need a refresh, Shannon is the inventor of the information age.  Have you heard of binary code, entropy in i...

Join the discussion on our Discord server As ML plays a more and more relevant role in many domains of everyday life, it’s quite obvious to see more and more attacks to ML systems. In this episode we talk about the most popular attacks against machine learning systems and some mitigations designed by researchers Ambra Demontis and Marco Melis, from the University of Cagliari (Italy). The guests ar...

Join the discussion on our Discord server Scaling technology and business processes are not equal. Since the beginning of the enterprise technology, scaling software has been a difficult task to get right inside large organisations. When it comes to Artificial Intelligence and Machine Learning, it becomes vastly more complicated.  In this episode I propose a framework - in five pillars - for the b...

Join the discussion on our Discord server In this episode, I am with Aaron Gokaslan , computer vision researcher, AI Resident at Facebook AI Research. Aaron is the author of OpenGPT-2, a parallel NLP model to the most discussed version that OpenAI decided not to release because too accurate to be published. We discuss about image-to-image translation, the dangers of the GPT-2 model and the future...

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 wit...

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 gene...