Program Highlights »
Sat Dec 10th 08:00 AM -- 06:30 PM @ Room 127 + 128
Constructive Machine Learning
Fabrizio Costa · Thomas Gärtner · Andrea Passerini · Francois Pachet

Workshop Home Page

In many real-world applications, machine learning algorithms are employed as a tool in a ''constructive process''. These processes are similar to the general knowledge-discovery process but have a more specific goal: the construction of one-or-more domain elements with particular properties. In this workshop we want to bring together domain experts employing machine learning tools in constructive processes and machine learners investigating novel approaches or theories concerning constructive processes as a whole. Interesting applications include but are not limited to: image synthesis, drug and protein design, computational cooking, generation of art (paintings, music, poetry). Interesting approaches include but are not limited to: deep generative learning, active approaches to structured output learning, transfer or multi-task learning of generative models, active search or online optimization over relational domains, and learning with constraints.

Many of the applications of constructive machine learning, including the ones mentioned above, are primarily considered in their respective application domain research area but are hardly present at machine learning conferences. By bringing together domain experts and machine learners working on constructive ML, we hope to bridge this gap between the communities.

08:30 AM Introduction
Fabrizio Costa, Andrea Passerini, Thomas Gärtner, Francois Pachet
08:45 AM Artificially-intelligent drug design
Gisbert Schneider
09:15 AM Chef Watson: Computational Creativity Applied To Recipes
Florian Pinel
09:45 AM Efficient optimization for probably submodular constraints in CRFs
Maxim Berman
10:00 AM A constructive approach for graph concepts with long range dependencies
Stefan Mautner, Fabrizio Costa
10:15 AM Constructive Layout Synthesis via Coactive Learning
Paolo Dragone, Andrea Passerini
11:00 AM Multiplicative and Fine-grained Gating for Reading Comprehension
Russ Salakhutdinov
11:30 AM Magenta
12:00 PM Modelling human appreciation of machine generated What-if ideas
Martin Žnidaršič, Janez Kranjc
12:00 PM Chord2Vec: Learning Musical Chord Embeddings
Christian Walder
12:00 PM Collaborative creativity with Monte-Carlo Tree Search and Convolutional Neural Networks
Memo Akten
12:00 PM A Machine Learning Approach to Support Music Creation by Musically Untrained People
Tetsuro Kitahara
01:30 PM Narrated Reality
Ross E Goodwin
02:00 PM Computational Creativity
Simon Colton
02:30 PM Fast Patch-based Style Transfer of Arbitrary Style
T. Q. (Ricky) Chen, Mark Schmidt
02:45 PM Out-of-class novelty generation: an experimental foundation
Balázs Kégl
03:30 PM Structured Prediction with Logged Bandit Feedback
Thorsten Joachims
04:00 PM Automatic Chemical Design using Variational Autoencoders
José Miguel Hernández-Lobato
04:30 PM Optimal Teaching for Online Perceptrons
Xuezhou Zhang, Jerry Zhu
04:30 PM C-RNN-GAN: Generative adversarial training of sequence models with continuous data
Olof Mogren
04:30 PM Generating Class-conditional Images with Gradient-based Inference
David Duvenaud
04:40 PM Poster Session
05:10 PM Panel Discussion
Gisbert Schneider, Ross E Goodwin, Simon Colton, Russ Salakhutdinov, Thorsten Joachims, Florian Pinel