Timezone: »
While early work on knowledge representation and inference was primarily symbolic, the corresponding approaches subsequently fell out of favor, and were largely supplanted by connectionist methods. In this workshop, we will work to close the gap between the two paradigms, and aim to formulate a new unified approach that is inspired by our current understanding of human cognitive processing. This is important to help improve our understanding of Neural Information Processing and build better Machine Learning systems, including the reuse of knowledge learned in one application domain in analogous domains.
The workshop brings together world leaders in the fields of neural computation, logic and artificial intelligence, natural language understanding, cognitive science, and computational neuroscience. Over the two workshop days, their invited lectures will be complemented with presentations based on contributed papers and poster sessions, giving ample opportunity to interact and discuss the different perspectives and emerging approaches.
The workshop targets a single broad theme of general interest to the vast majority of the NIPS community, namely the study of translations and ways of integration between neural models and knowledge representation for the purpose of achieving an effective integration of learning and reasoning. Neural-symbolic computing is now an established topic of wider interest to NIPS with topics that are relevant to almost everyone studying neural information processing.
Some of the relevant keywords characterizing the event are: neural-symbolic computing; language processing; cognitive agents; multimodal learning; deep networks; symbol manipulation; variable binding; integration of learning and reasoning.
Fri 5:40 a.m. - 6:00 a.m.
|
Neural-symbolic integration: Challenges, promises, perspectives, ideas
(
Talk
)
|
Tarek R. Besold 🔗 |
Fri 6:00 a.m. - 6:30 a.m.
|
Sum-Product Networks and Tractable Markov Logic: And End-to-End Neural-Symbolic System
(
Talk
)
|
Pedro Domingos 🔗 |
Fri 6:30 a.m. - 7:00 a.m.
|
Deep Symbolic Learning
(
Talk
)
|
Stephen H Muggleton 🔗 |
Fri 7:30 a.m. - 8:00 a.m.
|
Unifying Symbolic and Probabilistic Reasoning via Mixed Graphical Models
(
Talk
)
|
Rina Dechter 🔗 |
Fri 8:00 a.m. - 8:30 a.m.
|
Cognitive Foundations for Common-Sense Knowledge Representation and Reasoning
(
Talk
)
|
Josh Tenenbaum 🔗 |
Fri 8:30 a.m. - 9:00 a.m.
|
Discussion Panel with Morning Speakers (Day 1)
(
Discussion Panel
)
|
Pedro Domingos · Stephen H Muggleton · Rina Dechter · Josh Tenenbaum 🔗 |
Fri 12:30 p.m. - 1:00 p.m.
|
Reasoning with Memory Networks Successes and Challenges
(
Talk
)
|
Antoine Bordes 🔗 |
Fri 1:00 p.m. - 1:30 p.m.
|
Motivation
(
Talk
)
|
Ramanathan Guha 🔗 |
Fri 2:00 p.m. - 2:30 p.m.
|
How Can We Direct Our Agents?
(
Talk
)
|
Gregory Wayne 🔗 |
Fri 2:30 p.m. - 3:00 p.m.
|
Discussion Panel with Afternoon Speakers (Day 1)
(
Discussion Panel
)
|
Ramanathan Guha · Antoine Bordes · Gregory Wayne 🔗 |
Sat 5:30 a.m. - 6:00 a.m.
|
Turing Computation with Recurrent Artifcial Neural Networks
(
Talk
)
|
Giovanni S Carmantini 🔗 |
Sat 6:00 a.m. - 6:30 a.m.
|
Lifted Relational Neural Networks
(
Talk
)
|
Gustav Sourek 🔗 |
Sat 6:30 a.m. - 7:00 a.m.
|
Relational Knowledge Extraction from Neural Networks
(
talk
)
|
Artur Garcez 🔗 |
Sat 7:30 a.m. - 8:00 a.m.
|
Lifelong Machine Learning and Reasoning
(
Talk
)
|
Daniel Silver 🔗 |
Sat 8:00 a.m. - 8:30 a.m.
|
Dense Models and Reasoning
(
Talk
)
|
Michael J Witbrock 🔗 |
Sat 8:30 a.m. - 9:00 a.m.
|
Discussion Panel with Morning Speakers (Day 2)
(
Discussion Panel
)
|
Giovanni S Carmantini · Gustav Sourek · Artur Garcez · Daniel Silver · Michael J Witbrock 🔗 |
Sat 12:30 p.m. - 1:00 p.m.
|
Combinatorial structures and processing in Neural Blackboard Architectures
(
Talk
)
|
Frank van der Velde 🔗 |
Sat 1:00 p.m. - 1:30 p.m.
|
Four facts about TPRs
(
Talk
)
|
Paul Smolensky 🔗 |
Sat 2:00 p.m. - 2:30 p.m.
|
Putting the "neural" back in neural networks
(
Talk
)
|
Gary Marcus 🔗 |
Sat 2:30 p.m. - 3:00 p.m.
|
Discussion Panel with Afternoon Speakers (Day 2)
(
Discussion Panel
)
|
Frank van der Velde · Paul Smolensky · Gary Marcus 🔗 |
Author Information
Artur Garcez (City University London)
Tarek R. Besold (Free University of Bozen-Bolzano)
Risto Miikkulainen (The University of Texas at Austin)
Gary Marcus (New York University)
More from the Same Authors
-
2023 Poster: Efficient Activation Function Optimization through Surrogate Modeling »
Garrett Bingham · Risto Miikkulainen -
2020 Workshop: BabyMind: How Babies Learn and How Machines Can Imitate »
Byoung-Tak Zhang · Gary Marcus · Angelo Cangelosi · Pia Knoeferle · Klaus Obermayer · David Vernon · Chen Yu -
2020 : Opening Remarks: BabyMind, Byoung-Tak Zhang and Gary Marcus »
Byoung-Tak Zhang · Gary Marcus -
2017 : Representational primitives, in minds and machines »
Gary Marcus -
2017 Symposium: Metalearning »
Risto Miikkulainen · Quoc V Le · Kenneth Stanley · Chrisantha Fernando -
2016 : Summary/Goodbye »
Tarek R. Besold · Artur Garcez · Antoine Bordes · Gregory Wayne -
2016 : Invited talk Risto Miikkulainen (University of Texas at Austin & Sentient Technologies Inc., USA) »
Risto Miikkulainen -
2016 : Welcome/Opening »
Tarek R. Besold · Antoine Bordes · Gregory Wayne · Artur Garcez -
2016 Workshop: Cognitive Computation: Integrating Neural and Symbolic Approaches »
Tarek R. Besold · Antoine Bordes · Gregory Wayne · Artur Garcez -
2015 : Discussion Panel with Afternoon Speakers (Day 2) »
Frank van der Velde · Paul Smolensky · Gary Marcus -
2015 : Putting the "neural" back in neural networks »
Gary Marcus -
2015 : Discussion Panel with Morning Speakers (Day 2) »
Giovanni S Carmantini · Gustav Sourek · Artur Garcez · Daniel Silver · Michael J Witbrock -
2015 : Relational Knowledge Extraction from Neural Networks »
Artur Garcez -
2015 : Neural-symbolic integration: Challenges, promises, perspectives, ideas »
Tarek R. Besold