Le Cam meets LeCun: Deficiency and Generic Feature Learning
نویسندگان
چکیده
Deep Learning” methods attempt to learn generic features in an unsupervised fashion from a large unlabelled data set. These generic features should perform as well as the best hand crafted features for any learning problem that makes use of this data. We provide a definition of generic features, characterize when it is possible to learn them and provide algorithms closely related to the deep belief network and autoencoders of deep learning. In order to do so we use the notion of deficiency distance and illustrate its value in studying certain general learning problems.
منابع مشابه
Unsupervised Feature Learning from Temporal Data
Current state-of-the art object detection and recognition algorithms mainly use supervised training, and most benchmark datasets contain only static images. In this work we study feature learning in the context of temporally coherent video data. We focus on training convolutional features on unlabeled video data, using only the assumption that adjacent video frames contain semantically similar ...
متن کاملEffect generic and non-generic feedback on Motor Learning basketball free throw in Children
Non-generic feedback refers to a specific event and that task performance is the reason to the acquisition of skills and implies that performance is malleable, while generic feedback implies that task performance reflects an inherent ability. The Goal of this study was to determine the generic and non-generic feedback effects on children’s motor learning basketball free throw. This research was...
متن کاملInvariant Feature Learning on a Mobile Robot
Teaching a robot to perceive and navigate in an unstructured natural world is a difficult task. Without learning, navigation systems are short-range and extremely limited. With learning, the robot can be taught to classify terrain at longer distances, but these classifiers can be fragile as well, leading to extremely conservative planning. A robust, high-level learning-based perception system f...
متن کاملLearning to Linearize Under Uncertainty
Training deep feature hierarchies to solve supervised learning tasks has achieved state of the art performance on many problems in computer vision. However, a principled way in which to train such hierarchies in the unsupervised setting has remained elusive. In this work we suggest a new architecture and loss for training deep feature hierarchies that linearize the transformations observed in u...
متن کاملReading checks with multilayer graph transformer networks
Yann Le Cun L eon Bottou Yoshua Bengio Speech and Image Processing Services Research Lab AT&T Labs, 101 Crawfords Corner Road, Holmdel, NJ 07733, USA [email protected] ABSTRACT We propose a new machine learning paradigm called Multilayer Graph Transformer Network that extends the applicability of gradient-based learning algorithms to systems composed of modules that take graphs as input and...
متن کامل