Search
Now showing items 1-5 of 5
Hierarchically Local Tasks and Deep Convolutional Networks
(Center for Brains, Minds and Machines (CBMM), 2020-06-24)
The main success stories of deep learning, starting with ImageNet, depend on convolutional networks, which on certain tasks perform significantly better than traditional shallow classifiers, such as support vector machines. ...
A Definition of General Problem Solving
(2020-07-13)
What is general intelligence? What does it mean by general problem solving? We attempt to give a definition of general problem solving, characterize the common process of problem solving and provide a basic algorithm that ...
Universal Format Conversions
(2020-06-05)
Information is the fuel for intelligence. Any competitive intelligence system should be information hungry. “Formats” on the other hand, is the container for information. Accessing information without the ability to
decipher ...
Flexible Intelligence
(2020-06-18)
We discuss the problem of flexibility in intelligence, a relatively little-studied topic in machine learning and AI. Flexibility can be understood as out-of-distribution generalization, and it can be achieved by converting ...
Implicit dynamic regularization in deep networks
(Center for Brains, Minds and Machines (CBMM), 2020-08-17)
Square loss has been observed to perform well in classification tasks, at least as well as crossentropy. However, a theoretical justification is lacking. Here we develop a theoretical analysis for the square loss that also ...