Unveiling the Future of Machine Learning
Delve into the world of machine learning with a focus on the future and present applications, self-driving cars, and the key components needed for success. Explore topics such as online learning, reinforcement, language, reasoning, and more. Understand the importance of labeled data, learning predictors, and leveraging representation and optimization for success in the realm of machine learning.
Download Presentation
Please find below an Image/Link to download the presentation.
The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author. If you encounter any issues during the download, it is possible that the publisher has removed the file from their server.
You are allowed to download the files provided on this website for personal or commercial use, subject to the condition that they are used lawfully. All files are the property of their respective owners.
The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author.
E N D
Presentation Transcript
Machine Learning the Future http://hunch.net/~mltf John Langford Microsoft Research
Machine Learning in the present 1.Get a large amount of labeled data ?,?? where ? {1, ,1000} 2.Learn a predictor :? ? 3.Use the predictor. The Foundation: Samples + Representation + Optimization
Where is my self-driving car?
Other applications 1.Personalized medicine? 2.Conversational Agents? 3.Machine Translation? 4.Personal Assistants? 5.Your job?
How do we succeed? What is necessary for success? And what is a compatible solution?
Pieces to solve 1. Online learning: You can t redo everything. 2. Representation: Circuits >> gates 3. Reinforcement: good/bad is the real-world primitive 4. Exploration: infinite wrong data does not work 5. Language: Human language = ? 6. Reasoning: It can t all be reaction. 7. Memory: How did you get to class today? Solve all in a compatible way the future?
Exploration Supervised Learning =Representation +Optimization Active Bandits Contextual Bandit Contextual Decision Process Markov Decision Process Policy Improvement Q-learning Reinforcement
For today: revisit foundations. Why does this work? 1.Get a large amount of labeled data ?,?? where ? {1, ,1000} 2.Learn a classifier c:? ? 3.Use the classifier Success = Representation + Optimization + Labeled Samples
