#### Filter Results:

- Full text PDF available (12)

#### Publication Year

1978

2017

- This year (4)
- Last 5 years (12)
- Last 10 years (13)

#### Publication Type

#### Co-author

#### Journals and Conferences

#### Brain Region

#### Cell Type

#### Data Set Used

#### Key Phrases

#### Method

Learn More

- Alex Graves, Greg Wayne, Ivo Danihelka
- ArXiv
- 2014

We extend the capabilities of neural networks by coupling them to external memory resources, which they can interact with by attentional processes. The combined system is analogous to a Turing Machine or Von Neumann architecture but is differentiable end-toend, allowing it to be efficiently trained with gradient descent. Preliminary results demonstrate that… (More)

- Alex Graves, Greg Wayne, +17 authors Demis Hassabis
- Nature
- 2016

Artificial neural networks are remarkably adept at sensory processing, sequence learning and reinforcement learning, but are limited in their ability to represent variables and data structures and to store data over long timescales, owing to the lack of an external memory. Here we introduce a machine learning model called a differentiable neural computer… (More)

We present a unified framework for learning continuous control policies using backpropagation. It supports stochastic control by treating stochasticity in the Bellman equation as a deterministic function of exogenous noise. The product is a spectrum of general policy gradient algorithms that range from model-free methods with value functions to model-based… (More)

- Ivo Danihelka, Greg Wayne, Benigno Uria, Nal Kalchbrenner, Alex Graves
- ICML
- 2016

We investigate a new method to augment recurrent neural networks with extra memory without increasing the number of network parameters. The system has an associative memory based on complex-valued vectors and is closely related to Holographic Reduced Representations and Long Short-Term Memory networks. Holographic Reduced Representations have limited… (More)

- Ann C. Kennedy, Greg Wayne, Patrick Kaifosh, Karina Alviña, L. F. Abbott, Nathaniel Sawtell
- Nature neuroscience
- 2014

Mormyrid electric fish are a model system for understanding how neural circuits predict the sensory consequences of motor acts. Medium ganglion cells in the electrosensory lobe create negative images that predict sensory input resulting from the fish's electric organ discharge (EOD). Previous studies have shown that negative images can be created through… (More)

- Nicolas Heess, Dhruva TB, +9 authors David Silver
- ArXiv
- 2017

The reinforcement learning paradigm allows, in principle, for complex behaviours to be learned directly from simple reward signals. In practice, however, it is common to carefully hand-design the reward function to encourage a particular solution, or to derive it from demonstration data. In this paper explore how a rich environment can help to promote the… (More)

Neuroscience has focused on the detailed implementation of computation, studying neural codes, dynamics and circuits. In machine learning, however, artificial neural networks tend to eschew precisely designed codes, dynamics or circuits in favor of brute force optimization of a cost function, often using simple and relatively uniform initial architectures.… (More)

- Ziyu Wang, Josh Merel, Scott E. Reed, Greg Wayne, Nando de Freitas, Nicolas Heess
- ArXiv
- 2017

Deep generative models have recently shown great promise in imitation learning for motor control. Given enough data, even supervised approaches can do one-shot imitation learning; however, they are vulnerable to cascading failures when the agent trajectory diverges from the demonstrations. Compared to purely supervised methods, Generative Adversarial… (More)

- Adam H. Marblestone, Greg Wayne, Konrad P. Körding
- Front. Comput. Neurosci.
- 2016

Neuroscience has focused on the detailed implementation of computation, studying neural codes, dynamics and circuits. In machine learning, however, artificial neural networks tend to eschew precisely designed codes, dynamics or circuits in favor of brute force optimization of a cost function, often using simple and relatively uniform initial architectures.… (More)

- Mevlana Gemici, Chia-Chun Hung, +5 authors Timothy P. Lillicrap
- ArXiv
- 2017

We consider the general problem of modeling temporal data with long-range dependencies, wherein new observations are fully or partially predictable based on temporally-distant, past observations. A sufficiently powerful temporal model should separate predictable elements of the sequence from unpredictable elements, express uncertainty about those… (More)