This is a machine-learning-focused Podcast, where we interview people in the field of Artificial Intelligence and discuss interesting technical topics of Machine Learning. In the episodes, we focus on business-related use-cases (especially with Deep Learning ) and we also try to bring some technical white papers to the ground, not forgetting on the way that there are always some people behind the technology, so we try to understand their motivation and drive.
http://mlcafe.libsyn.com/website
Gesamtlänge aller Episoden: 13 hours 44 minutes
episode 6: Finding the label errors with Cleanlab with Curtis Northcutt - 006
What is a confident joint of the labels? How can you find label errors in your dataset? With an easy-to-use tool called Cleanlab.
episode 5: A New Deep Learning Optimizer called Ranger with Less Wright - 005
Do you use the right Deep Learning optimizer? It is worth to take a look at Ranger which outperforms a lot of other optimizers.
episode 4: Cutting-Edge Gradient Descent Variants with Levente Szabados - 004
The Deep Learning community focuses much on NN architectures, however, optimizers are also important, we take a look at Gradient Descent and its variants in this episode.
episode 3: Tree-based methods for procurement & are expert systems alive? with Renee Ahel - 003
Interview with Renee Ahel about Machine Learning techniques in Procurement.
episode 2: Can we predict the accuracy of a Neural Network? Yes, with the WeightWatcher tool by Charles Martin, Ph.D. - 002
In this episode we do a deep dive into deep neural networks. What conclusions can we make looking at the distribution of eigenvalues of each layer?
episode 1: Progressively Growing GANs & Style GANs with Alexandr Honchar - 001
In this episode, we talked about the idea behind GANs in general and two special types of GANs: Progressively Growing GANs and Style GANs. LinkedIn URL of Alexandr Honchar: https://www.linkedin.com/in/alexandr-honchar-4423b962/ Companies where Alex...