1
Competitive Programming with AlphaCode
Solving novel problems and setting a new milestone in competitive programming.
DeepMind Blog
Build AI responsibly to benefit humanity
- Popular posts
- 56
- Total points
- 17,568
- HN comments
- 6,278
- Rank
- #37 company
Visit deepmind.com → On Hacker News Jul 2016 – Jun 2023
AI & Machine Learning 55Science & Space 13Software Engineering 12Games & Graphics 12Tech Industry & Business 5Open Source 3
2
WaveNet: A Generative Model for Raw Audio
This post presents WaveNet, a deep generative model of raw audio waveforms. We show that WaveNets are able to generate speech which mimics any human voice and which sounds more natural than the best existing Text-to-Speech systems, reducing the gap with human performance by over 50%.
3
DeepMind: A Generalist Agent
Explore a selection of our recent research on some of the most complex and interesting challenges in AI.
4
Differentiable Neural Computers
In a recent study in Nature, we introduce a form of memory-augmented neural network called a differentiable neural computer, and show that it can learn to use its memory to answer questions about complex, structured data, including artificially generated stories, family trees, and even a map of the London Underground…
5
Learning to write programs that generate images
Through a human’s eyes, the world is much more than just the images reflected in our corneas. For example, when we look at a building and admire the intricacies of its design, we can appreciate the craftsmanship it requires. This ability to interpret objects through the tools that created them gives us a richer…
6
Understanding Deep Learning Through Neuron Deletion
Deep neural networks are composed of many individual neurons, which combine in complex and counterintuitive ways to solve a wide range of challenging tasks. This complexity grants neural networks their power but also earns them their reputation as confusing and opaque black boxes.
7
Population-based training of neural networks
Neural networks have shown great success in everything from playing Go and Atari games to image recognition and language translation. But often overlooked is that the success of a neural network at a particular application is often determined by a series of choices made at the start of the research, including what…
8
Enabling Continual Learning in Neural Networks
Computer programs that learn to perform tasks also typically forget them very quickly. We show that the learning rule can be modified so that a program can remember old tasks when learning a new one. This is an important step towards more intelligent programs that are able to learn progressively and adaptively.
9
Preserving Outputs Precisely while Adaptively Rescaling Targets
Multi-task learning - allowing a single agent to learn how to solve many different tasks - is a longstanding objective for artificial intelligence research. Recently, there has been a lot of excellent progress, with agents like DQN able to use the same algorithm to learn to play multiple games including Breakout and…
10
Tackling multiple tasks with a single visual language model
We introduce Flamingo, a single visual language model (VLM) that sets a new state of the art in few-shot learning on a wide range of open-ended multimodal tasks.
11
Reinforcement learning with unsupervised auxiliary tasks
Our primary mission at DeepMind is to push the boundaries of AI, developing programs that can learn to solve any complex problem without needing to be taught how. Our reinforcement learning agents have achieved breakthroughs in Atari 2600 games and the game of Go. Such systems, however, can require a lot of data and a…
12
Competitive programming with AlphaCode
Solving novel problems and setting a new milestone in competitive programming.