In this interview, Jonathan Schwarz of Google DeepMind shares insight on Deep Learning projects. He offers tips and advice for the those interested in DL, and explains whether DL projects relate to other data driven projects? He comments on effective team size, software, frameworks, common mistakes, resources for learning, and more all under 30 minutes. Have a good lunch!
Jonathan Schwarz is a Computer Engineer with a MSc in Machine Learning from The University of Edinburgh, he is currently working as a Research Engineer at Google DeepMind in London, UK.
1:50 Ideal deep learning project. DL Teams. Similarities with other Machine Learning projects.
3:32 Extension of DLs projects. Iteration cycles.
4:22 Most challenging parts of DL projects.
7:31 Tips for deep learning projects: teams, software and frameworks.
10:52 Common mistakes when you are starting with DL.
13:22 When DL is the right method, when DL is NOT the right method.
16:07 Recommendations for companies evaluating to start a DL project.
19:09 State of the art of DL and predictions for 5 years time.
22:04 The problem of overconfidence errors.
23:36 The problem of Natural Language Understanding.
24:28 Recommended resources:
Machine Learning Coursera
Pattern Recognition and Machine Learning by Christopher M. Bishop.
The Elements of Statistical Learning: Data Mining, Inference, and Prediction by Trevor Hastie, Robert Tibshirani, and Jerome Friedman.
Bayesian Reasoning and Machine Learning.
26:48 Closing words and advices for DL.
I've worked in BI, DWH, and Data Mining. MSc in Data Science. Experience in multiple BI and Data Science tools always thinking how to solve information needs and add value to organisations from the data available. Experience with Business Objects, Pentaho, Informatica Power Center, SSAS, SSIS, SSRS, MS SQL Server from 2000 to 2017, and other DBMS, Tableau, Hadoop, Python, R, SQL. Predicting modelling. My interest are in Information Systems, Data Modeling, Predictive and Descriptive Analysis, Machine Learning, Data Visualization, Open Data. Specialties: Data modeling, data warehousing, data mining, performance management, business intelligence.