Estimating the uncertainty of a Bayesian model has been investigated for decades. The model posterior is almost always intractable, such that approximation is necessary. In many real-world cases, even though a decent estimation of the model posterior is obtained, another approximation is required to compute the predictive distribution over the desired output. A common accurate solution is to use Monte Carlo (MC) integration. However, it needs to maintain a large number of samples, evaluate the model repeatedly and average multiple model outputs. In this paper, we propose a method to approximate the probability distribution over the simplex induced by model posterior, enabling tractable computation of the predictive distribution for classification. The aim is to approximate the induced uncertainty of a specific Bayesian model, meanwhile alleviating the heavy workload of MC integration in testing time. Methodologically, we adapt Wasserstein distance to learn the induced conditional distributions, which is novel for Bayesian learning. The proposed method is universally applicable to Bayesian classification models that allow for posterior sampling. Empirical results validate the strong practical performance of our approach.

With the advent of deep neural networks, some research focuses towards understanding their black-box behavior. In this paper, we propose a new type of self-interpretable models, that are, architectures designed to provide explanations along with their predictions. Our method proceeds in two stages and is trained end-to-end: first, our model builds a low-dimensional binary representation of any input where each feature denotes the presence or absence of concepts. Then, it computes a prediction only based on this binary representation through a simple linear model. This allows an easy interpretation of the model's output in terms of presence of particular concepts in the input. The originality of our approach lies in the fact that concepts are automatically discovered at training time, without the need for additional supervision. Concepts correspond to a set of patterns, built on local low-level features (e.g a part of an image, a word in a sentence), easily identifiable from the other concepts. We experimentally demonstrate the relevance of our approach using classification tasks on two types of data, text and image, by showing its predictive performance and interpretability.

As Europe (together with Australia and Israel) are glued to their TV sets watching the 64th Eurovision song competition, we asked ourselves What makes a Eurovision song memorable? We are a group of artists, musicians and programmers that wanted explore human creativity and challenge it. We have created a Eurovision AI song that celebrates Eurovision – its melodrama, kitsch and camp, its humor and its gimmicks. The result is comprised entirely of material written and composed by Artificial Intelligence, titled "Blue Jeans & Bloody Tears". The project team fed hundreds of Eurovision songs – melodies and lyrics – into a neuron network.

New Zealand is a leader in government use of artificial intelligence (AI). It is part of a global network of countries that use predictive algorithms in government decision making, for anything from the optimal scheduling of public hospital beds to whether an offender should be released from prison, based on their likelihood of reoffending, or the efficient processing of simple insurance claims . But the official use of AI algorithms in government has been in the spotlight in recent years .

Domino's Pizza has introduced a pizza checker enabled by artificial intelligence in a move designed to tackle a frequent complaint from customers: that the pizza they receive does not closely resemble the image of the pizza they ordered. The DOM Pizza Checker uses a smart scanner that sits above the pizza cutting bench and checks the quality of every pizza. I It is now operating in all Domino's stores across Australia and New Zealand. The system has been developed by Domino's and Perth based Dragontail Systems. Source: Domino's delivers artificially intelligent pizzas

It's 7.40am on Monday morning and Stiofan Sexton is about to do something he has never done before – and he doesn't even know it. Waiting on the platform at Sydney's Chatswood station, he is one of the first thousand passengers on the new fully driverless Metro Northwest in its first weekday rush-hour test. He used to take a slow bus up to work in North Ryde. Now he steps on to a carriage that goes up to 100km/h, along a 66km track, with service every four minutes, all run by a single computer. Asked by Guardian Australia how he feels about the fully automated train, he says he did not realise it was.

New Zealand is a leader in government use of artificial intelligence (AI). It is part of a global network of countries that use predictive algorithms in government decision making, for anything from the optimal scheduling of public hospital beds to whether an offender should be released from prison, based on their likelihood of reoffending, or the efficient processing of simple insurance claims. But the official use of AI algorithms in government has been in the spotlight in recent years. On the plus side, AI can enhance the accuracy, efficiency and fairness of day-to-day decision making. But concerns have also been expressed regarding transparency, meaningful human control, data protection and bias.

Reinforcement learning in multi-agent scenarios is important for real-world applications but presents challenges beyond those seen in single-agent settings. We present an actor-critic algorithm that trains decentralized policies in multi-agent settings, using centrally computed critics that share an attention mechanism which selects relevant information for each agent at every timestep. This attention mechanism enables more effective and scalable learning in complex multi-agent environments, when compared to recent approaches. Our approach is applicable not only to cooperative settings with shared rewards, but also individualized reward settings, including adversarial settings, as well as settings that do not provide global states, and it makes no assumptions about the action spaces of the agents. As such, it is flexible enough to be applied to most multi-agent learning problems.

Machine learning tasks such as optimizing the hyper-parameters of a model for a new dataset or few-shot learning can be vastly accelerated if they are not done from scratch for every new dataset, but carry over findings from previous runs. Meta-learning makes use of features of a whole dataset such as its number of instances, its number of predictors, the means of the predictors etc., so called meta-features, dataset summary statistics or simply dataset characteristics, which so far have been hand-crafted, often specifically for the task at hand. More recently, unsupervised dataset encoding models based on variational auto-encoders have been successful in learning such characteristics for the special case when all datasets follow the same schema, but not beyond. In this paper we design a novel model, Dataset2Vec, that is able to characterize datasets with a latent feature vector based on batches and thus is able to generalize beyond datasets having the same schema to arbitrary (tabular) datasets. To do so, we employ auxiliary learning tasks on batches of datasets, esp. to distinguish batches from different datasets. We show empirically that the meta-features collected from batches of similar datasets are concentrated within a small area in the latent space, hence preserving similarity. We also show that using the dataset characteristics learned by Dataset2Vec in a state-of-the-art hyper-parameter optimization model outperforms the hand-crafted meta-features that have been used in the hyper-parameter optimization literature so far. As a result, we advance the current state-of-the-art results for hyper-parameter optimization.

Due to their hunger for big data, modern deep learning models are trained in parallel, often in distributed environments, where communication of model updates is the bottleneck. Various update compression (e.g., quantization, sparsification, dithering) techniques have been proposed in recent years as a successful tool to alleviate this problem. In this work, we introduce a new, remarkably simple and theoretically and practically effective compression technique, which we call natural compression (NC). Our technique is applied individually to all entries of the to-be-compressed update vector and works by randomized rounding to the nearest (negative or positive) power of two. NC is "natural" since the nearest power of two of a real expressed as a float can be obtained without any computation, simply by ignoring the mantissa. We show that compared to no compression, NC increases the second moment of the compressed vector by the tiny factor 9/8 only, which means that the effect of NC on the convergence speed of popular training algorithms, such as distributed SGD, is negligible. However, the communications savings enabled by NC are substantial, leading to 3-4x improvement in overall theoretical running time. For applications requiring more aggressive compression, we generalize NC to natural dithering, which we prove is exponentially better than the immensely popular random dithering technique. Our compression operators can be used on their own or in combination with existing operators for a more aggressive combined effect. Finally, we show that N is particularly effective for the in-network aggregation (INA) framework for distributed training, where the update aggregation is done on a switch, which can only perform integer computations.