Peter T. Kazlas

Demonstration venue · read-only. Every page can be browsed; the buttons that would change it are switched off. Create an account to run TaxoReview on your own data. A simulation from public publication records: the people listed were not invited and did not agree to review.

? Tutorial for this page

Demo Data from EDBT 2026 / reviewers in the wild / expert

dblp:78/2002 · DBLP profile ↗

← Back

2ranked-venue papers

1as first author

0since 2021 · last 1994

—ORCID · none

Domains — the database's venue-derived domains; a paper can count in several

Artificial intelligence and machine learning · 1 · 1 first-authorSystems, architecture and hardware · 1

Expertise — from the expertise taxonomy: the topics of the expert's papers under the CCF categories. A weight counts papers with recency: 1 for a paper about the topic, 0.3 when the topic is its context, halved every five years.

Artificial intelligence

1 paper

Reinforcement learning · 75% Time series and sequential data · 25%

Topics — the 4 heaviest of 4, each with the papers that count most for it

Topic	Papers	Last	Evidence papers
Machine learning › Time series and sequential data › time series modeling multi-step prediction	1	1994	Direct Multi-Step Time Series Prediction Using TD-lambda · NIPS 1994
Machine learning › Reinforcement learning › temporal difference learning › eligibility traces TD(lambda)	1	1994	Direct Multi-Step Time Series Prediction Using TD-lambda · NIPS 1994
Machine learning › Reinforcement learning temporal difference learning	1	1994	Direct Multi-Step Time Series Prediction Using TD-lambda · NIPS 1994
Machine learning › Reinforcement learning value function approximation	1	1994	Direct Multi-Step Time Series Prediction Using TD-lambda · NIPS 1994

Methods — techniques the papers use, named apart from their topics

temporal difference learning · 0.0

Year	Publication	Venue	Position
1994	Direct Multi-Step Time Series Prediction Using TD-lambda Peter T. Kazlas, Andreas S. Weigend	NIPS	1
1993	Neural system design with the integrated neurocomputing architecture abstract Design and implementation issues of high-performance VLSI systems in the form of deployable neural networks for pattern recognition applications are addressed, in particular the integrated neurocomputing architecture (INCA), which was developed with a complete system approach involving the integration of custom analog IC design, digital and analog board-level design, neural network development software, and application-specific hardware and software elements, is considered. The design methodology is discussed to demonstrate the capability of INCA as a usable neuroprocessing system. It serves as an example of a system that highlights many design automation issues for future mixed-signal, highly integrated systems.> Paul Mukai, Mark Busa, Peter T. Kazlas	Great Lakes Symposium on VLSI	3