Where I express personal thoughts in words
Josh Tobin is the founder and CEO of a stealth machine learning startup. Previously, Josh worked as a deep learning & robotics researcher at OpenAI and as a management consultant at McKinsey. He is also the creator of Full Stack Deep Learning, the first course focused on the emerging engineering discipline of production machine learning. Josh did his Ph.D. in Computer Science at UC Berkeley, advised by Pieter Abbeel.
Meta-learning, also known as learning how to learn, has recently emerged as a potential learning paradigm that can learn information from one task and generalize that information to unseen tasks proficiently. During this quarantine time, I started watching lectures on Stanford’s CS 330 class on Deep Multi-Task and Meta Learning taught by the brilliant Chelsea Finn. As a courtesy of her lectures, this blog post attempts to answer these key questions:
Why do we need meta-learning?
How does the math of meta-learning work?
What are the different approaches to design a meta-learning algorithm?
Sara Hooker is a researcher at Google Brain doing deep learning research on reliable explanations of model predictions for black-box models. Her main research interests gravitate towards interpretability, model compression, and security. In 2014, she founded Delta Analytics, a non-profit dedicated to bringing technical capacity to help non-profits across the world use machine learning for good. She grew up in Africa, in Mozambique, Lesotho, Swaziland, South Africa, and Kenya. Her family now lives in Monrovia, Liberia.
Colleen M. Farrelly is a data scientist whose experience spans biotech, healthcare, pharma, marketing, finance, operations, edtech, manufacturing, and disaster logistics. Her research focuses mostly on the intersection of topology/geometry, machine learning, statistics, and quantum computing. She’s passionate about poetry, surfing, Gators football, and socioeconomics.
Parul Pandey is a Data Science Evangelist at H2O.ai. She combines Data Science, evangelism and community in her work. Her emphasis is to break down the data science jargon for the people. Prior to H2O.ai, she worked with Tata Power India, applying Machine Learning and Analytics to solve the pressing problem of load sheddings in India. She is also an active writer and speaker and has contributed to various national and international publications including Towards Data Science, Analytics Vidhya, and KDNuggets and Datacamp.
Dr. Leonard Apeltsin is a research fellow at the Berkeley Institute for Data Science. He holds a Ph.D. in Biomedical Informatics from UCSF and a BS in Biology and Computer Science from Carnegie Mellon University. Leonard was a Senior Data Scientist & Engineering Lead at Primer AI, a machine learning company that specializes in using advanced Natural Language Processing Techniques to analyze terabytes of unstructured text data. As a founding team-member, Leonard helped expand the Primer AI team from four employees to over 80 people. Outside of Data Science and ML, Leonard enjoys scuba diving, salsa dancing, and making short documentary films.
Vincent Tatan is a Data and Technology enthusiast with relevant working experiences from Google LLC, Visa Inc., and Lazada to implement microservice architectures, business intelligence, and analytics pipeline projects. Vincent is a native Indonesian with a record of accomplishments in problem-solving with strengths in Full Stack Development, Data Analytics, and Strategic Planning. He has been actively consulting Singapore Management University’s Business Intelligence and Analytics Club, guiding aspiring data scientists and engineers from various backgrounds and opening up his expertise for businesses to develop their products. Vincent also opens up his one on one mentorship service to coach on landing your dream Data Analyst/Engineer Job at Google, Visa, or other large tech companies.
In this post and those to follow, I will be walking through the creation and training of recommendation systems, as I am currently working on this topic for my Master Thesis. Part 4 looks into the nitty-gritty mathematical details of matrix factorization, arguably the most common baseline model for recommendation system research these days.
