ngd-vis
Understand the learning behavior of natural gradient descent vs SGD and other optimization methods
view repo
An extensive body of empirical research has revealed remarkable regularities in the acquisition, organization, deployment, and neural representation of human semantic knowledge, thereby raising a fundamental conceptual question: what are the theoretical principles governing the ability of neural networks to acquire, organize, and deploy abstract knowledge by integrating across many individual experiences? We address this question by mathematically analyzing the nonlinear dynamics of learning in deep linear networks. We find exact solutions to this learning dynamics that yield a conceptual explanation for the prevalence of many disparate phenomena in semantic cognition, including the hierarchical differentiation of concepts through rapid developmental transitions, the ubiquity of semantic illusions between such transitions, the emergence of item typicality and category coherence as factors controlling the speed of semantic processing, changing patterns of inductive projection over development, and the conservation of semantic similarity in neural representations across species. Thus, surprisingly, our simple neural model qualitatively recapitulates many diverse regularities underlying semantic development, while providing analytic insight into how the statistical structure of an environment can interact with nonlinear deep learning dynamics to give rise to these regularities.
READ FULL TEXT
The human brain is a dynamical system whose extremely complex sensor-dri...
read it
Despite the widespread practical success of deep learning methods, our
t...
read it
In this paper, we hypothesize that the effects of the degree of typicali...
read it
Motivated by the idea that criticality and universality of phase transit...
read it
We present a study of the manners by which Domain information has been
i...
read it
Lately there has been a lot of discussion about why deep learning algori...
read it
This book develops an effective theory approach to understanding deep ne...
read it
Understand the learning behavior of natural gradient descent vs SGD and other optimization methods
Comments
There are no comments yet.