Michigan State University
Optimality and hierarchical representation in emergent neural Turing machines and their visual navigation
Abstract
dc:description"Traditional Turing Machines (TMs) are symbolic in the sense that representations in these TMs are static and hand-crafted. This paper presents a new kind of TM - emergent neural Turing Machine. By neural, we mean that the control of the TM has neurons as basic computing elements. By emergent, we mean that the internal representations are formed during learning without hand-crafting. Developmental Network-1 (DN-1) uses emergent representation to perform Turing Computation but the internal hierarchy is handcrafted with emergent features. The major novelty of the proposed TM (Developmental Network-2) over DN-1 is that the representational hierarchy inside DN-2 is emergent and fluid. DN-2 grows complex hierarchies by dynamically allowing initialization of neurons with different domains of connection. Its optimality in terms of maximum likelihood properties is established under the conditions of limited learning experience and resources. Although DN-2 is meant for general learning tasks, we experimented with a complex task-- vision-guided navigation in simulated and natural worlds using DN-2. Real-world and simulated navigation experiments showed that DN-2 successfully learned rules of navigation with image and other inputs. The formed hierarchical representation in DN-2 focuses on important navigation features like road edges while disregarding the distractors like shadows edges."--Page ii.
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Zheng, Zejia
- Contributors dc:contributor
-
- Weng, Juyang
Subjects
dc:subject × 4Rights
dc:rights- Statement dc:rights
-
- In Copyright
- Language dc:language
- English
Identifiers
dc:identifier.*- Identifier
-
etd:16320
isbn:9780355849097
isbn:0355849097
oclc:1047957127
umi:10789741
local:Zheng_grad.msu_0128D_15916