In this episode I continue the conversation from the previous one, about failing machine learning models.
When data scientists have access to the distributions of training and testing datasets it becomes relatively easy to assess if a model will perform equally on both datasets. What happens with private datasets, where no access to the data can be granted?
At fitchain we might have an answer to this fundamental problem.
Improving your AI by finding issues within data pockets (Ep. 195)
Fake data that looks, feels, and behaves like production.(Ep.194)
Batteries and AI in Automotive (Ep. 193)
Collect data at the edge [RB] (Ep. 192)
Bayesian Machine Learning with Ravin Kumar (Ep. 191)
What is spatial data science? With Matt Forest from Carto (Ep. 190)
Connect. Collect. Normalize. Analyze. An interview with the people from Railz AI (Ep. 189)
History of data science [RB] (Ep. 188)
Artificial Intelligence and Cloud Automation with Leon Kuperman from Cast.ai (Ep. 187)
Embedded Machine Learning: Part 5 - Machine Learning Compiler Optimization (Ep. 186)
Embedded Machine Learning: Part 4 - Machine Learning Compilers (Ep. 185)
Embedded Machine Learning: Part 3 - Network Quantization (Ep. 184)
Embedded Machine Learning: Part 2 (Ep. 183)
Embedded Machine Learning: Part 1 (Ep.182)
History of Data Science (Ep. 181)
Capturing Data at the Edge (Ep. 180)
[RB] Composable Artificial Intelligence (Ep. 179)
What is a data mesh and why it is relevant (Ep. 178)
Environmentally friendly AI (Ep. 177)
Do you fear of AI? Why? (Ep. 176)
Create your
podcast in
minutes
It is Free
Insight Story: Tech Trends Unpacked
Zero-Shot
Fast Forward by Tomorrow Unlocked: Tech past, tech future
The Unbelivable Truth - Series 1 - 26 including specials and pilot
A Prairie Home Companion: News from Lake Wobegon