Data Science at Home

254 Episodes

1. Why sharing real data is dangerous (Ep. 97)

   Published: 1/03/2020
2. Building reproducible machine learning in production (Ep. 96)

   Published: 22/02/2020
3. Bridging the gap between data science and data engineering: metrics (Ep. 95)

   Published: 14/02/2020
4. A big welcome to Pryml: faster machine learning applications to production

   Published: 7/02/2020
5. It's cold outside. Let's speak about AI winter (Ep. 93)

   Published: 31/12/2019
6. The dark side of AI: bias in the machine (Ep. 92)

   Published: 28/12/2019
7. The dark side of AI: metadata and the death of privacy (Ep. 91)

   Published: 23/12/2019
8. The dark side of AI: recommend and manipulate (Ep. 90)

   Published: 11/12/2019
9. The dark side of AI: social media and the optimization of addiction (Ep. 89)

   Published: 3/12/2019
10. How to improve the stability of training a GAN (Ep. 88)

    Published: 18/11/2019
11. What if I train a neural network with random data? (with Stanisław Jastrzębski) (Ep. 87)

    Published: 12/11/2019
12. Deeplearning is easier when it is illustrated (with Jon Krohn) (Ep. 86)

    Published: 5/11/2019
13. More powerful deep learning with transformers (Ep. 84)

    Published: 27/10/2019
14. What is wrong with reinforcement learning? (Ep. 82)

    Published: 15/10/2019
15. Have you met Shannon? Conversation with Jimmy Soni and Rob Goodman about one of the greatest minds in history (Ep. 81)

    Published: 10/10/2019
16. Attacking machine learning for fun and profit (with the authors of SecML Ep. 80)

    Published: 1/10/2019
17. [RB] How to scale AI in your organisation (Ep. 79)

    Published: 26/09/2019
18. Replicating GPT-2, the most dangerous NLP model (with Aaron Gokaslan) (Ep. 78)

    Published: 23/09/2019
19. How to generate very large images with GANs (Ep. 76)

    Published: 6/09/2019
20. How to cluster tabular data with Markov Clustering (Ep. 73)

    Published: 20/08/2019