Deep learning is a promising machine learning technique with a high barrier to entry. In this talk, we provide an easy entry into this field via "deep features" from pre-trained models. These features can be trained on one data set for one task and used to obtain good predictions on a different task, on a different data set. We demonstrate our technique using our open source based GraphLab Create framework.
YOU MAY ALSO LIKE:
- Leonardo De Marchi's Deep Learning Fundamentals (in London on 22nd - 23rd October 2019)
- Practical ML 2020 (in London on 2nd - 3rd July 2020)
- Reinforcement Learning Journal Club (in London on 17th October 2019)
- PowerBI, The Must-Know Speed Up Tricks (in London on 17th October 2019)
- Automating Elaborate-Transform-Load for Busy Data Scientists (SkillsCast recorded in October 2019)
- Apache Druid: the fast, real-time, open-source analytics data store (SkillsCast recorded in September 2019)
Deep Learning Made Easy With Reusable Deep Features
Danny Bickson is VP EMEA and Co-Founder at Dato. Previously he was a research scientist at Carnegie Mellon University and one of the creators of GraphLab open source project. Danny has a PhD in distributed algorithms from the Hebrew University.