Neural Audio Synthesis of Musical Notes with WaveNet Autoencoders
- Jesse Engel, Cinjon Resnick, K. Simonyan
- Computer ScienceInternational Conference on Machine Learning
- 5 April 2017
A powerful new WaveNet-style autoencoder model is detailed that conditions an autoregressive decoder on temporal codes learned from the raw audio waveform, and NSynth, a large-scale and high-quality dataset of musical notes that is an order of magnitude larger than comparable public datasets is introduced.
Pommerman: A Multi-Agent Playground
- Cinjon Resnick, W. Eldridge, Joan Bruna
- Computer ScienceAIIDE Workshops
- 19 September 2018
Pommerman, a multi-agent environment based on the classic console game Bomberman, consists of a set of scenarios, each having at least four players and containing both cooperative and competitive aspects.
Backplay: "Man muss immer umkehren"
- Cinjon Resnick, R. Raileanu, Sanyam Kapoor, Alex Peysakhovich, Kyunghyun Cho, Joan Bruna
- Computer ScienceArXiv
- 18 July 2018
The approach, Backplay, uses a single demonstration to construct a curriculum for a given task, and analytically characterize the types of environments where Backplay can improve training speed and compare favorably to other competitive methods known to improve sample efficiency.
Capacity, Bandwidth, and Compositionality in Emergent Language Learning
- Cinjon Resnick, Abhinav Gupta, Jakob N. Foerster, Andrew M. Dai, Kyunghyun Cho
- Computer ScienceAdaptive Agents and Multi-Agent Systems
- 24 October 2019
The hypothesis is that there should be a specific range of model capacity and channel bandwidth that induces compositional structure in the resulting language and consequently encourages systematic generalization.
Ridge Rider: Finding Diverse Solutions by Following Eigenvectors of the Hessian
- Jack Parker-Holder, Luke Metz, J. Foerster
- Computer ScienceNeural Information Processing Systems
- 12 November 2020
Ridge Rider offers a promising direction for a variety of challenging problems by iteratively following and branching amongst the ridges of the Hessian, and effectively span the loss surface to find qualitatively different solutions.
Audio Deepdream: Optimizing raw audio with convolutional networks
- Adam Roberts, Cinjon Resnick, Diego Ardila, D. Eck
- Computer Science
- 2016
This work has followed in the footsteps of Van den Oord et al and trained a network to predict embeddings that were themselves the result of a collaborative filtering model, which creates a chain of differentiable functions from raw audio to high level features.
Probing the State of the Art: A Critical Look at Visual Representation Evaluation
- Cinjon Resnick, Zeping Zhan, Joan Bruna
- Computer ScienceArXiv
- 30 November 2019
This work shows that this test is insufficient and that models which perform poorly on linear classification can perform strongly (weakly) on more involved tasks like temporal activity localization.
Compositionality and Capacity in Emergent Languages
- Abhinav Gupta, Cinjon Resnick, Jakob N. Foerster, Andrew M. Dai, Kyunghyun Cho
- Computer ScienceWorkshop on Representation Learning for NLP
- 1 July 2020
This paper investigates the learning biases that affect the efficacy and compositionality in multi-agent communication in addition to the communicative bandwidth and explores how the capacity of a neural network impacts its ability to learn a compositional language.
In-Distribution Interpretability for Challenging Modalities
- Cosmas Heiß, R. Levie, Cinjon Resnick, G. Kutyniok, Joan Bruna
- Computer ScienceArXiv
- 1 July 2020
This work displays the flexibility of the intuitive framework which utilizes generative models to improve on the meaningfulness of such explanations of deep neural networks: music and physical simulations of urban environments.
Vehicle Community Strategies
- Cinjon Resnick, I. Kulikov, Kyunghyun Cho, J. Weston
- Computer ScienceArXiv
- 19 April 2018
This work considers self-driving cars coordinating with each other and focuses on how communication influences the agents' collective behavior, finding that communication helps (most) with adverse conditions.
...
...