Iskalni niz:
išči po
išči po
išči po
išči po
Vrsta gradiva:
Jezik:
Št. zadetkov: 6
Learning for Control from Multiple Demonstrations
Adam Coates
Video in druga učna gradiva
Oznake: computer science;machine learning;reinforcement learning;artificial intelligence
We consider the problem of learning to follow a desired trajectory when given a small number of demonstrations from a sub-optimal expert. We present an algorithm that (i) extracts the---initially unknown---desired trajectory from the sub-optimal expert's demonstrations and (ii) learns a local model ...
Leto: 2008 Vir: videolectures.net
Scalable Learning in Computer Vision
Adam Coates
Video in druga učna gradiva
Oznake: computer science;computer vision
Computer vision is a challenging application area of machine learning. Recent work has shown that large training sets may yield higher performance in vision tasks like object detection. We overview our work in object detection using a scalable, distributed training system capable of training on more ...
Leto: 2009 Vir: videolectures.net
Deep Learning for Machine Vision
Adam Coates
Video in druga učna gradiva
Oznake: computer science;computer vision;machine learning
Machine learning algorithms have freed practitioners from many error-prone, hand-engineered components for making decisions in common machine vision tasks such as object recognition. A major source of difficulty, however, is that such learning systems still rely on many hand-built components like so ...
Leto: 2013 Vir: videolectures.net
Deep Learning (hopefully faster)
Adam Coates
Video in druga učna gradiva
Oznake: computer science;machine learning;deep learning;reinforcement learning;unsupervised learning
Leto: 2015 Vir: videolectures.net
Speech Recognition and Deep Learning
Adam Coates
Video in druga učna gradiva
Oznake: computer science;machine learning;deep learning;reinforcement learning;unsupervised learning
Leto: 2015 Vir: videolectures.net
34. The Stanford Autonomous Helicopter
Pieter Abbeel , Adam Coates , Andrew Ng
Video in druga učna gradiva
Oznake: computer science;robotics
Stanford's Autonomous Helicopter project pushes the limits of autonomous flight control by teaching a computer to fly a competition-class remote controlled (RC) helicopter through a range of aerobatic stunts. Our apprenticeship learning approach learns to fly the helicopter by observing human demons ...
Leto: 2009 Vir: videolectures.net
Št. zadetkov: 6
Ključne besede:
Leto izdaje:
Repozitorij:
Tipologija:
Jezik: