Now showing items 11-20 of 20
Human-like Learning: A Research Proposal
We propose Human-like Learning, a new machine learning paradigm aiming at training generalist AI systems in a human-like manner with a focus on human-unique skills.
Theory of Deep Learning IIb: Optimization Properties of SGD
(Center for Brains, Minds and Machines (CBMM), 2017-12-27)
In Theory IIb we characterize with a mix of theory and experiments the optimization of deep convolutional networks by Stochastic Gradient Descent. The main new result in this paper is theoretical and experimental evidence ...
Multi-stage Multi-recursive-input Fully Convolutional Networks for Neuronal Boundary Detection
(Center for Brains, Minds and Machines (CBMM), 2017-10-01)
In the field of connectomics, neuroscientists seek to identify cortical connectivity comprehensively. Neuronal boundary detection from the Electron Microscopy (EM) images is often done to assist the automatic reconstruction ...
Learning Mid-Level Auditory Codes from Natural Sound Statistics
(Center for Brains, Minds and Machines (CBMM), arXiv, 2017-01-25)
Interaction with the world requires an organism to transform sensory signals into representations in which behaviorally meaningful properties of the environment are made explicit. These representations are derived through ...
Do Deep Neural Networks Suffer from Crowding?
(Center for Brains, Minds and Machines (CBMM), arXiv, 2017-06-26)
Crowding is a visual effect suffered by humans, in which an object that can be recognized in isolation can no longer be recognized when other objects, called flankers, are placed close to it. In this work, we study the ...
Object-Oriented Deep Learning
(Center for Brains, Minds and Machines (CBMM), 2017-10-31)
We investigate an unconventional direction of research that aims at converting neural networks, a class of distributed, connectionist, sub-symbolic models into a symbolic level with the ultimate goal of achieving AI ...
Exact Equivariance, Disentanglement and Invariance of Transformations
Invariance, equivariance and disentanglement of transformations are important topics in the field of representation learning. Previous models like Variational Autoencoder  and Generative Adversarial Networks  attempted ...
Theory of Intelligence with Forgetting: Mathematical Theorems Explaining Human Universal Forgetting using “Forgetting Neural Networks”
(Center for Brains, Minds and Machines (CBMM), 2017-12-05)
In  we suggested that any memory stored in the human/animal brain is forgotten following the Ebingghaus curve – in this follow-on paper, we define a novel algebraic structure, a Forgetting Neural Network, as a simple ...
Full interpretation of minimal images
(Center for Brains, Minds and Machines (CBMM), 2017-02-08)
The goal in this work is to model the process of ‘full interpretation’ of object images, which is the ability to identify and localize all semantic features and parts that are recognized by human observers. The task is ...
Theory of Deep Learning III: explaining the non-overfitting puzzle
THIS MEMO IS REPLACED BY CBMM MEMO 90 A main puzzle of deep networks revolves around the absence of overfitting despite overparametrization and despite the large capacity demonstrated by zero training error on randomly ...