██████████████████████████████████████████████████████████████████████
Neural Abstract Machines & Program Induction (NAMPI) v2.0, FAIM 2018
When: July 15, 2018
Where: Stockholmsmässan, Stockholm, Sweden
Web: https://uclmr.github.io/nampi/
██████████████████████████████████████████████████████████████████████
██ DESCRIPTION ██
Machine intelligence capable of learning complex procedural behavior, inducing (latent) programs, and reasoning with these programs is a key to solving artificial intelligence. The problems of learning procedural behavior and program induction have been studied from different perspectives in many computer science fields such as program synthesis, probabilistic programming, inductive logic programming, reinforcement learning, and recently in deep learning. However, despite the common goal, there seems to be little communication and collaboration between the different fields focused on this problem. Recently, there have been a lot of success stories in the deep learning community related to learning neural networks capable of using trainable memory abstractions. This has led to the development of neural networks with differentiable data structures such as Differentiable Neural Computers, Memory Networks, Neural Stacks, and Hierarchical Attentive Memory, as well as complex differentiable interpreters able to combine differentiable structures with program induction and execution. Simultaneously, neural program induction models like Neural Program Interpreters and Neural Programmer and DeepCoder have created a lot of excitement in the field, promising induction of algorithmic behavior, programs, and enabling inclusion of programming languages in the processes of execution and induction, while staying end-to-end trainable. Trainable program induction models have the potential to make a substantial impact in many problems involving long-term memory, reasoning, and procedural execution, such as question answering, dialog, and robotics. The aim of the NAMPI workshop is to bring researchers and practitioners from both academia and industry, in the areas of deep learning, program synthesis, probabilistic programming, programming languages, inductive programming and reinforcement learning, together to exchange ideas on the future of program induction with a special focus on neural network models and abstract machines. Through this workshop we look to identify common challenges, exchange ideas among and lessons learned from the different fields, as well as establish a (set of) standard evaluation benchmark(s) for approaches that learn with abstraction and/or reason with induced programs.
██ CALL FOR PAPERS ██
We encourage visionary and position papers, as well as work-in-progress submissions. We also accept previously published papers and cross-submissions, but will not include them in the workshop proceedings.
-- Standard Workshop Paper
The submissions for regular workshop papers should be substantially original and novel. They should not exceed more than 4 pages, excluding references. The submissions should be anonymised as we will strive to organise a double-blind review with open comments on beta.openreview.net. In case double-blind review will not be available upon time of submission, we will do a single-blind review. Authors will be expected to present a poster, and the camera-ready versions must be uploaded to arXiv, as it will be displayed on the workshop webpage. The papers should be submitted to https://openreview.net/group?id=ICML.cc/2018/Workshop/NAMPI
-- Work-in-progress & cross-submissions
Preliminary work and cross-submissions can be submitted as a 2 page extended abstract. The authors will be expected to present a poster, however these papers do not count as NAMPI workshop papers and will not be included in the workshop proceedings. Interested authors should submit their extended abstracts to nampi@googlegroups.com. Papers in this category do not need to be anonymised and their selection will be determined at the discretion of the organising committee.
All submissions should be typeset in ICML format.
Areas of interest for discussion and submissions include, but are not limited to:
- Applications
- Compositionality in Representation Learning
- Differentiable Memory
- Differentiable Data Structures
- Function and (sub-)Program Compositionality
- Inductive Logic Programming
- Knowledge Representation in Neural Abstract Structures
- Large-scale Program Induction
- Machine learning -guided programming
- Meta-Learning and Self-improving
- Neural Abstract Machines
- Optimisation methods for Program Induction
- Program Induction: Datasets, Tasks, and Evaluation
- Program Synthesis
- Probabilistic Programming
- Reinforcement Learning for Program Induction
- Semantic Parsing
██ KEY DATES ██
Paper submission deadline: June 8th
Notification of acceptance: June 23rd
Final Papers Due: June 27th
NAMPI workshop: July 15th
Deadlines are at 11:59pm PDT.
██ INVITED SPEAKERS ██
- Richard Evans (DeepMind)
- Brenden Lake (New York University)
- Veselin Raychev (DeepCode)
- Rishabh Singh (Google Brain)
- Satinder Singh (University of Michigan)
- Armando Solar-Lezama (Massachusetts Institute of Technology)
- Dawn Song (UC Berkeley)
██ ORGANISERS ██
- Matko Bošnjak (University College London)
- Pushmeet Kohli (DeepMind)
- Tejas Kulkarni (Massachusetts Institute of Technology and DeepMind)
- Sebastian Riedel (University College London)
- Tim Rocktäschel (University of Oxford)
- Dawn Song (UC Berkeley)
- Rob Zinkov (University of Oxford)
██ SPONSORS ██
██ TRAVEL BURSARIES ██
Thanks to our generous sponsors, we will be able to support a few travel bursaries. Preference will be given to (student) authors of admitted papers. For more details and the application drop us a line at nampi@googlegroups.com.