Data Science at Home

Technology, machine learning and algorithms. Come join the discussion! https://discord.gg/4UNKGf3

Episodes Date

One of the best features of neural networks and machine learning models is to memorize patterns from training data and apply those to unseen observations. That's where the magic is. However, there are...
March 23, 2020
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 o...
March 14, 2020
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 bu...
March 8, 2020
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.    
March 1, 2020
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 ...
February 22, 2020
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 dat...
February 14, 2020
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 se...
February 7, 2020
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 inflate...
December 31, 2019
  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...
December 28, 2019
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”, usu...
December 23, 2019
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 g...
December 11, 2019
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 ...
December 3, 2019
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 kno...
November 28, 2019
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 t...
November 18, 2019
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 generalisat...
November 12, 2019

Load more