1 code implementation • 19 Mar 2024 • Takuya Akiba, Makoto Shing, Yujin Tang, Qi Sun, David Ha
Surprisingly, our Japanese Math LLM achieved state-of-the-art performance on a variety of established Japanese LLM benchmarks, even surpassing models with significantly more parameters, despite not being explicitly trained for such tasks.
1 code implementation • 5 Aug 2022 • Aleksandar Stanić, Yujin Tang, David Ha, Jürgen Schmidhuber
We show that current agents struggle to generalize, and introduce novel object-centric agents that improve over strong baselines.
no code implementations • 18 Apr 2022 • Yingtao Tian, Marco Cuturi, David Ha
Recent advances in deep learning, such as powerful generative models and joint text-image embeddings, have provided the computational creativity community with new tools, opening new perspectives for artistic pursuits.
2 code implementations • 13 Apr 2022 • Federico Pigozzi, Yujin Tang, Eric Medvet, David Ha
We show experimentally that the evolved robots are effective in the task of locomotion: thanks to self-attention, instances of the same controller embodied in the same robot can focus on different inputs.
1 code implementation • 10 Feb 2022 • Yujin Tang, Yingtao Tian, David Ha
Evolutionary computation has been shown to be a highly effective method for training neural networks, particularly when employed at scale on CPU clusters.
no code implementations • 29 Nov 2021 • David Ha, Yujin Tang
In this review, we will provide a historical context of neural network research's involvement with complex systems, and highlight several active areas in modern deep learning research that incorporate the principles of collective intelligence to advance its current capabilities.
no code implementations • 19 Nov 2021 • Forrest Huang, Eldon Schoop, David Ha, Jeffrey Nichols, John Canny
Sketching is a natural and effective visual communication medium commonly used in creative processes.
1 code implementation • 18 Sep 2021 • Yingtao Tian, David Ha
Evolutionary algorithms have been used in the digital art scene since the 1970s.
3 code implementations • NeurIPS 2021 • Yujin Tang, David Ha
In complex systems, we often observe complex global behavior emerge from a collection of agents interacting with each other in their environment, with each individual agent acting only on locally available information, without knowing the full picture.
1 code implementation • 15 May 2020 • Miguel González-Duque, Rasmus Berg Palm, David Ha, Sebastian Risi
The approach can reliably find levels with a specific target difficulty for a variety of planning agents in only a few trials, while maintaining an understanding of their skill landscape.
no code implementations • 12 May 2020 • Forrest Huang, Eldon Schoop, David Ha, John Canny
Iteratively refining and critiquing sketches are crucial steps to developing effective designs.
3 code implementations • 18 Mar 2020 • Yujin Tang, Duong Nguyen, David Ha
Inattentional blindness is the psychological phenomenon that causes one to miss things in plain sight.
1 code implementation • 25 Dec 2019 • Alex Lamb, Sherjil Ozair, Vikas Verma, David Ha
In this work we focus on their ability to have invariance towards the presence or absence of details.
2 code implementations • NeurIPS 2019 • C. Daniel Freeman, Luke Metz, David Ha
That useful models can arise out of the messy and slow optimization process of evolution suggests that forward-predictive modeling can arise as a side-effect of optimization under the right circumstances.
Model-based Reinforcement Learning reinforcement-learning +1
1 code implementation • NeurIPS 2019 • Adam Gaier, David Ha
We demonstrate that our method can find minimal neural network architectures that can perform several reinforcement learning tasks without weight training.
2 code implementations • ICCV 2019 • Raphael Gontijo Lopes, David Ha, Douglas Eck, Jonathon Shlens
Dramatic advances in generative models have resulted in near photographic quality for artificially rendered faces, animals and other objects in the natural world.
10 code implementations • 3 Dec 2018 • Tarin Clanuwat, Mikel Bober-Irizar, Asanobu Kitamoto, Alex Lamb, Kazuaki Yamamoto, David Ha
Much of machine learning research focuses on producing models which perform well on benchmark tasks, in turn improving our understanding of the challenges associated with those tasks.
Ranked #4 on Image Classification on Kuzushiji-MNIST (Error metric)
9 code implementations • 12 Nov 2018 • Danijar Hafner, Timothy Lillicrap, Ian Fischer, Ruben Villegas, David Ha, Honglak Lee, James Davidson
Planning has been very successful for control tasks with known environment dynamics.
Ranked #2 on Continuous Control on DeepMind Walker Walk (Images)
1 code implementation • 9 Oct 2018 • David Ha
In this work, we explore the possibility of learning a version of the agent's design that is better suited for its task, jointly with the policy.
no code implementations • NeurIPS 2018 • David Ha, Jürgen Schmidhuber
A generative recurrent neural network is quickly trained in an unsupervised manner to model popular reinforcement learning environments through compressed spatio-temporal representations.
21 code implementations • 27 Mar 2018 • David Ha, Jürgen Schmidhuber
We explore building generative neural network models of popular reinforcement learning environments.
no code implementations • 13 Feb 2018 • Natasha Jaques, Jennifer McCleary, Jesse Engel, David Ha, Fred Bertsch, Rosalind Picard, Douglas Eck
We use a Latent Constraints GAN (LC-GAN) to learn from the facial feedback of a small group of viewers, by optimizing the model to produce sketches that it predicts will lead to more positive facial expressions.
19 code implementations • ICLR 2018 • David Ha, Douglas Eck
We present sketch-rnn, a recurrent neural network (RNN) able to construct stroke-based drawings of common objects.
1 code implementation • 30 Jan 2017 • Chrisantha Fernando, Dylan Banarse, Charles Blundell, Yori Zwols, David Ha, Andrei A. Rusu, Alexander Pritzel, Daan Wierstra
It is a neural network algorithm that uses agents embedded in the neural network whose task is to discover which parts of the network to re-use for new tasks.
Ranked #5 on Continual Learning on F-CelebA (10 tasks)
8 code implementations • 27 Sep 2016 • David Ha, Andrew Dai, Quoc V. Le
This work explores hypernetworks: an approach of using a one network, also known as a hypernetwork, to generate the weights for another network.
Ranked #14 on Language Modelling on Penn Treebank (Character Level)