AGI 2015 - PDF Preprint Papers

AGI 2015

Teaser Browsing | Click Here

Title Browsing | Click Here

Wall of Fame | Most Viewed AGI-2015 Paper

click to vote

AGI
2015

35views Artificial Intelligence» more AGI 2015»

Are There Deep Reasons Underlying the Pathologies of Today's Deep Learning Algorithms?

8 years 7 months ago

Download goertzel.org

Abstract. Some currently popular and successful deep learning architectures display certain pathological behaviors (e.g. conﬁdently classifying random data as belonging to a fami...

Ben Goertzel

claim paper

Read More »

Disclaimer and Copyright Notice

Sciweavers respects the rights of all copyright holders and in this regard, authors are only allowed to share a link to their preprint paper on their own website. Every contribution is associated with a desciptive image. It is the sole responsibility of the authors to ensure that their posted image is not copyright infringing. This service is compliant with IEEE copyright.

Id	Views	Title	Status

1	35	Are There Deep Reasons Underlying the Pathologies of Today's Deep Learning Algorithms?	claim
2	35	Bounded Cognitive Resources and Arbitrary Domains	claim
3	34	Anchoring Knowledge in Interaction: Towards a Harmonic Subsymbolic/Symbolic Framework and Architecture of Computational Cognition	claim
4	31	Can Machines Learn Logics?	claim
5	29	Assumptions of Decision-Making Models in AGI	claim
6	25	Issues in Temporal and Causal Inference	claim
7	24	Plan Recovery in Reactive HTNs Using Symbolic Planning	claim
8	23	Anytime Bounded Rationality	claim
9	23	Analysis of Types of Self-Improving Software	claim
10	22	Toward Tractable Universal Induction Through Recursive Program Learning	claim
11	21	Genetic Programming on Program Traces as an Inference Engine for Probabilistic Languages	claim
12	21	Modeling Motivation in MicroPsi 2	claim
13	20	Comparing Computer Models Solving Number Series Problems	claim
14	19	Decision-Making During Language Understanding by Intelligent Agents	claim
15	18	Safe Baby AGI	claim
16	17	Observation, Communication and Intelligence in Agent-Based Systems	claim
17	16	Optimization Framework with Minimum Description Length Principle for Probabilistic Programming	claim
18	16	Inferring Human Values for Safe AGI Design	claim
19	16	Scene Based Reasoning	claim
20	15	A New View on Grid Cells Beyond the Cognitive Map Hypothesis	claim
21	15	Emotional Concept Development	claim
22	15	On the Limits of Recursively Self-Improving AGI	claim
23	15	Towards Human-Level Inductive Functional Programming	claim
24	15	Instrumental Properties of Social Testbeds	claim
25	13	Ultimate Intelligence Part I: Physical Completeness and Objectivity of Induction	claim
26	13	Two Attempts to Formalize Counterpossible Reasoning in Deterministic Settings	claim
27	13	Using Localization and Factorization to Reduce the Complexity of Reinforcement Learning	claim
28	13	From Specialized Syntax to General Logic: The Case of Comparatives	claim

Sciweavers

Explore & Download

Productivity Tools

Document Tools

Image Tools

Sciweavers