News

Neural scene representation and rendering

There is more than meets the eye when it comes to how we understand a visual scene: our brains draw on prior knowledge to reason and to make inferences that go far beyond the patterns of light that hit our retinas. For example, when entering a room for the first time, you instantly recognise the items it contains and where they are positioned. If you see three legs of a table, you will infer that there is probably a fourth leg with the same shape and colour hidden from view.

Intel’s New Path to Quantum Computing

Intel’s director of quantum hardware, Jim Clarke, explains the company’s two quantum computing technologies The limits of Tangle Lake’s technology Silicon spin qubits and how far away they are The importance of cryogenic control electronics Top quantum computing applications What problems keeps him up at night AI vs. Quantum Computing: which will be more important? IEEE Spectrum: What’s special about Tangle Lake?

AI chip startup Wave to buy Silicon Valley old-timer MIPS

AI Nationalism

The last few years have seen developments in machine learning research and commercialisation that have been pretty astounding. As just a few examples: Image recognition starts to achieve human-level accuracy at complex tasks, for example skin cancer classification. Big steps forward in applying neural networks to machine translation at Baidu, Google, Microsoft etc.

The 50 Best Free Datasets for Machine Learning

What are some open datasets for machine learning? We at Gengo decided to create the ultimate cheat sheet for high quality datasets. These range from the vast (looking at you, Kaggle) or the highly specific (data for self-driving cars).

Liquid-air energy storage: The latest new “battery” on the UK grid

The Lifespan of a Lie – the Stanford Prison Experiment

Improving Language Understanding with Unsupervised Learning

We’ve obtained state-of-the-art results on a suite of diverse language tasks with a scalable, task-agnostic system, which we’re also releasing. Our approach is a combination of two existing ideas: transformers and unsupervised pre-training. These results provide a convincing example that pairing supervised learning methods with unsupervised pre-training works very well; this is an idea that many have explored in the past, and we hope our result motivates further research into applying this idea on larger and more diverse datasets.

Attacks against machine learning – an overview

At a high level, attacks against classifiers can be broken down into three types: Adversarial inputs, which are specially crafted inputs that have been developed with the aim of being reliably misclassified in order to evade detection. Adversarial inputs include malicious documents designed to evade antivirus, and emails attempting to evade spam filters. Data poisoning attacks, which involve feeding training adversarial data to the classifier.

Why do neural networks generalize so poorly?

Deep convolutional network architectures are often assumed to guarantee generalization for small image translations and deformations. In this paper we show that modern CNNs (VGG16, ResNet50, and InceptionResNetV2) can drastically change their output when an image is translated in the image plane by a few pixels, and that this failure of generalization also happens with other realistic small image transformations. Furthermore, the deeper the network the more we see these failures to generalize.