mirror of
https://github.com/google-deepmind/deepmind-research.git
synced 2026-02-06 03:32:18 +08:00
73 lines
4.4 KiB
Markdown
73 lines
4.4 KiB
Markdown
# DeepMind Research
|
|
|
|
This repository contains implementations and illustrative code to accompany
|
|
DeepMind publications. Along with publishing papers to accompany research
|
|
conducted at DeepMind, we release open-source
|
|
[environments](https://deepmind.com/research/open-source/open-source-environments/),
|
|
[data sets](https://deepmind.com/research/open-source/open-source-datasets/),
|
|
and [code](https://deepmind.com/research/open-source/open-source-code/) to
|
|
enable the broader research community to engage with our work and build upon it,
|
|
with the ultimate goal of accelerating scientific progress to benefit society.
|
|
For example, you can build on our implementations of the
|
|
[Deep Q-Network](https://github.com/deepmind/dqn) or
|
|
[Differential Neural Computer](https://github.com/deepmind/dnc), or experiment
|
|
in the same environments we use for our research, such as
|
|
[DeepMind Lab](https://github.com/deepmind/lab) or
|
|
[StarCraft II](https://github.com/deepmind/pysc2).
|
|
|
|
If you enjoy building tools, environments, software libraries, and other
|
|
infrastructure of the kind listed below, you can view open positions to work in
|
|
related areas on our [careers page](https://deepmind.com/careers/).
|
|
|
|
For a full list of our publications, please see
|
|
https://deepmind.com/research/publications/
|
|
|
|
## Projects
|
|
|
|
* [Characterizing signal propagation to close the performance gap in unnormalized ResNets](nfnets), ICLR 2021
|
|
* [Uncovering the Limits of Adversarial Training against Norm-Bounded Adversarial Examples](adversarial_robustness)
|
|
* [Functional Regularisation for Continual Learning](functional_regularisation_for_continual_learning), ICLR 2020
|
|
* [Self-Supervised MultiModal Versatile Networks](mmv), NeurIPS 2020
|
|
* [ODE-GAN: Training GANs by Solving Ordinary Differential Equations](ode_gan), NeurIPS 2020
|
|
* [Algorithms for Causal Reasoning in Probability Trees](causal_reasoning)
|
|
* [Gated Linear Networks](gated_linear_networks), NeurIPS 2020
|
|
* [Value-driven Hindsight Modelling](himo), NeurIPS 2020
|
|
* [Targeted free energy estimation via learned mappings](learned_free_energy_estimation), Journal of Chemical Physics 2020
|
|
* [Learning to Simulate Complex Physics with Graph Networks](learning_to_simulate), ICML 2020
|
|
* [Physically Embedded Planning Problems](physics_planning_games)
|
|
* [PolyGen: PolyGen: An Autoregressive Generative Model of 3D Meshes](polygen), ICML 2020
|
|
* [Bootstrap Your Own Latent](byol)
|
|
* [Catch & Carry: Reusable Neural Controllers for Vision-Guided Whole-Body Tasks](catch_carry), SIGGRAPH 2020
|
|
* [MEMO: A Deep Network For Flexible Combination Of Episodic Memories](memo), ICLR 2020
|
|
* [RL Unplugged: Benchmarks for Offline Reinforcement Learning](rl_unplugged)
|
|
* [Disentangling by Subspace Diffusion (GEOMANCER)](geomancer), NeurIPS 2020
|
|
* [What can I do here? A theory of affordances in reinforcement learning](affordances_theory), ICML 2020
|
|
* [Scaling data-driven robotics with reward sketching and batch reinforcement learning](sketchy), RSS 2020
|
|
* [The Option Keyboard: Combining Skills in Reinforcement Learning](option_keyboard), NeurIPS 2019
|
|
* [VISR - Fast Task Inference with Variational Intrinsic Successor Features](visr), ICLR 2020
|
|
* [Unveiling the predictive power of static structure in glassy systems](glassy_dynamics), Nature Physics 2020
|
|
* [Multi-Object Representation Learning with Iterative Variational Inference (IODINE)](iodine)
|
|
* [AlphaFold CASP13](alphafold_casp13), Nature 2020
|
|
* [Unrestricted Adversarial Challenge](unrestricted_advx)
|
|
* [Hierarchical Probabilistic U-Net (HPU-Net)](hierarchical_probabilistic_unet)
|
|
* [Training Language GANs from Scratch](scratchgan), NeurIPS 2019
|
|
* [Temporal Value Transport](tvt), Nature Communications 2019
|
|
* [Continual Unsupervised Representation Learning (CURL)](curl), NeurIPS 2019
|
|
* [Unsupervised Learning of Object Keypoints (Transporter)](transporter), NeurIPS 2019
|
|
* [BigBiGAN](bigbigan), NeurIPS 2019
|
|
* [Deep Compressed Sensing](cs_gan), ICML 2019
|
|
* [Side Effects Penalties](side_effects_penalties)
|
|
* [PrediNet Architecture and Relations Game Datasets](PrediNet)
|
|
* [Unsupervised Adversarial Training](unsupervised_adversarial_training), NeurIPS 2019
|
|
* [Graph Matching Networks for Learning the Similarity of Graph Structured
|
|
Objects](graph_matching_networks), ICML 2019
|
|
* [REGAL: Transfer Learning for Fast Optimization of Computation Graphs](regal)
|
|
* [Deep Ensembles: A Loss Landscape Perspective](ensemble_loss_landscape)
|
|
|
|
|
|
|
|
|
|
## Disclaimer
|
|
|
|
*This is not an official Google product.*
|