Academic Commons

Theses Doctoral

Autogenerative Networks

Chang, Oscar

Artificial intelligence powered by deep neural networks has seen tremendous improvements in the last decade, achieving superhuman performance on a diverse range of tasks. Many worry that it can one day develop the ability to recursively self-improve itself, leading to an intelligence explosion known as the Singularity. Autogenerative networks, or neural networks generating neural networks, is one major plausible pathway towards realizing this possibility. The object of this thesis is to study various challenges and applications of small-scale autogenerative networks in domains such as artificial life, reinforcement learning, neural network initialization and optimization, gradient-based meta-learning, and logical networks. Chapters 2 and 3 describe novel mechanisms for generating neural network weights and embeddings. Chapters 4 and 5 identify problems and propose solutions to fix optimization difficulties in differentiable mechanisms of neural network generation known as Hypernetworks. Chapters 6 and 7 study implicit models of network generation like backpropagating through gradient descent itself and integrating discrete solvers into continuous functions. Together, the chapters in this thesiscontribute novel proposals for non-differentiable neural network generation mechanisms, significant improvements to existing differentiable network generation mechanisms, and an assimilation of different learning paradigms in autogenerative networks.

Files

  • thumnail for Chang_columbia_0054D_16362.pdf Chang_columbia_0054D_16362.pdf application/pdf 3.8 MB Download File

More About This Work

Academic Units
Computer Science
Thesis Advisors
Lipson, Hod
Degree
Ph.D., Columbia University
Published Here
January 25, 2021