Amsterdam

Modelling the distribution of natural images is a landmark problem in unsupervised learning. We train a deep recurrent neural network to sequentially predict the pixels in an image. The network models the discrete joint probability of the raw pixel values. The distribution, though formally simple, can be arbitrarily complex and multimodal. The distribution is tractable and its ability to...

In this work we aim to solve a large collection of tasks using a single reinforcement learning agent with a single set of parameters. A key challenge is to handle the increased amount of data and extended training time, which is already a problem in single task learning. In order to tackle this challenging problem, we have developed a new distributed agent architecture IMPALA (Importance-...

Recurrent neural networks (RNNs) sequentially process data by updating their state with each new data point, and have long been the de facto choice for sequence modeling tasks. However, their inherently sequential computation makes them slow to train. Feed-forward and convolutional architectures have recently been shown to achieve superior results on some sequence modeling tasks such as machine...

Recent progress in the field of reinforcement learning has been accelerated by virtual learning environments such as video games, where novel algorithms and ideas can be quickly tested in a safe and reproducible manner. We introduce the Google Research Football Environment, a new reinforcement learning environment where agents are trained to play football in an advanced, physics-based 3D...

We present a neural architecture for sequences, the ByteNet, that has two core features: it runs in time that is linear in the length of the sequences and it preserves the sequences' temporal resolution. The ByteNet is a stack of two dilated convolutional neural networks, one to encode the source and one to decode the target, where the target decoder unfolds dynamically to generate variable...

The unconditional generation of high fidelity images is a longstanding benchmark for testing the performance of image decoders. Autoregressive image models have been able to generate small images unconditionally, but the extension of these methods to large images where fidelity can be more readily assessed has remained an open problem. Among the major challenges are the capacity to encode the...

Semi-supervised learning (SSL) provides a powerful framework for leveraging unlabeled data when labels are limited or expensive to obtain. Approaches based on deep neural networks have recently proven successful on standard benchmark tasks. However, we argue that these benchmarks do not reflect real-world requirements and are compared to weak baselines. We propose a set of new benchmarks and...

Semi-supervised learning has proven to be a powerful paradigm for leveraging unlabeled data to mitigate the reliance on large labeled datasets. In this work, we unify the current dominant approaches for semi-supervised learning to produce a new algorithm called MixMatch. MixMatch works by guessing low-entropy la- bels for data-augmented unlabeled examples, and then mixes labeled and unlabeled...

This work tackles the problem of semi-supervised learning of image classifiers. Our main insight is that the field of semi-supervised learning can benefit from the quickly advancing field of self-supervised visual representation learning. Unifying these two approaches, we propose the framework of self-supervised semi-supervised learning (S4L) and use it to derive two novel semi-supervised image...

An experimental science is only as strong as the veracity of its experiments – when experiments are not reproducible, researchers struggle to place their work on solid footing and progress is hampered. Many fields have had reproducibility crises. Some have recently recognized this as a problem in machine learning as well. One way to make research more reproducible is to make it easier to...

Learning meaningful and useful task-dependent data representations requires many training instances -- but training labels are expensive to obtain, and may be of varying quality. This creates a fundamental quality-versus-quantity trade-off in the learning process. Do we learn from the small amount of high-quality data or the potentially large amount of weakly-labeled data (obtained from...

In this paper, we propose a method for training neural networks when we have a large set of data with weak labels and a small amount of data with true labels. In our proposed model, we train two neural networks: a target network, the learner and a confidence network, the meta-learner. The target network is optimized to perform a given task and is trained using a large set of unlabeled data that...

A key challenge for RGB-D segmentation is how to effectively incorporate 3D geometric information from the depth channel into 2D appearance features. We propose to model the effective receptive field of 2D convolution based on the scale and locality from the 3D neighborhood. Standard convolutions are local in the image space (u, v), often with a fixed receptive field of 3x3 pixels. We propose...

We are interested in learning visual representations which allow for 3D manipulations of visual objects based on a single 2D image. We cast this into an image-to-image transformation task, and propose Iterative Generative Adversarial Networks (IterGANs) which iteratively transform an input image into an output image. Our models learn a visual representation that can be used for objects seen in...