We consider the problem of anomaly detection in images, and present a new detectiontechnique. Givenasampleofimages,allknowntobelongtoa"normal" class (e.g., dogs), we show how to train a deep neural model that can detect out-of-distribution images (i.e., non-dog objects).

Whilecurrentevaluationofthese systems typically assumes fixed working points based on pre-defined rejection thresholds, methodological progress requires benchmarking the general performance of systems akin to the AUROC in standard classification. In this work, we define 5 requirements for multi-threshold metrics in selective classification regarding task alignment, interpretability, and flexibility, and show how current approaches fail to meet them.

Temporal Knowledge Graph (TKG), which characterizes temporally evolving facts in the form of (subject, relation, object, timestamp), has attracted much attention recently. TKG reasoning aims to predict future facts based on given historical ones. However, existing TKG reasoning models are unable to abstain from predictions they are uncertain, which will inevitably bring risks in real-world applications. Thus, in this paper, we propose an abstention mechanism for TKG reasoning, which helps the existing models make selective, instead of indiscriminate, predictions. Specifically, we develop a confidence estimator, called Confidence Estimator with History (CEHis), to enable the existing TKG reasoning models to first estimate their confidence in making predictions, and then abstain from those with low confidence. To do so, CEHis takes two kinds of information into consideration, namely, the certainty of the current prediction and the accuracy of historical predictions. Experiments with representative TKG reasoning models on two benchmark datasets demonstrate the effectiveness of the proposed CEHis.

Intel today announced a strategic business and technology collaboration with Deci to optimize machine learning on the former's processors. Deci says that in the coming weeks, it will work with Intel to deploy "innovative AI technologies" to the companies' mutual customers. Machine learning deployments have historically been constrained by the size and speed of algorithms and the need for costly hardware. In fact, a report from MIT found that machine learning might be approaching computational limits. A separate Synced study estimated that the University of Washington's Grover fake news detection model cost $25,000 to train in about two weeks.

Students from the Technion's Henry and Marilyn Taub Faculty of Computer Science in Haifa, Nadav Bhonker (already graduated) and Shunit Haviv Hakimi, together with their advisor Professor Ran El-Yaniv have shown that it is possible to model and optimize personalized jazz preferences using artificial intelligence. Their paper on the research called the BebopNet project was published in the Proceedings of 21st International Society of Music Information Retrieval Conference. To people involved in the development of artificial intelligence technologies this is great news. The idea that something artistic, especially a field as personalized as jazz, can be recreated by AI is a major breakthrough. AI is a form of computer and as such can only really do what it has been pre-programmed to do and nothing as original as the composition of new and truly artistic sounding music.

Deep learning startup Deci today announced that it raised $9.1 million in a seed funding round led by Israel-based Emerge. According to a spokesperson, the company plans to devote the proceeds to customer acquisition efforts as it expands its Tel Aviv workforce. Machine learning deployments have historically been constrained by the size and speed of algorithms and the need for costly hardware. In fact, a report from MIT found that machine learning might be approaching computational limits. A separate Synced study estimated that the University of Washington's Grover fake news detection model cost $25,000 to train in about two weeks.

We consider the problem of selective prediction (also known as reject option) in deep neural networks, and introduce SelectiveNet, a deep neural architecture with an integrated reject option. Existing rejection mechanisms are based mostly on a threshold over the prediction confidence of a pre-trained network. In contrast, SelectiveNet is trained to optimize both classification (or regression) and rejection simultaneously, end-to-end. The result is a deep neural network that is optimized over the covered domain. In our experiments, we show a consistently improved risk-coverage trade-off over several well-known classification and regression datasets, thus reaching new state-of-the-art results for deep selective classification.

Inductive learning is based on inferring a general rule from a finite data set and using it to label new data. In transduction one attempts to solve the problem of using a labeled training set to label a set of unlabeled points, which are given to the learner prior to learning. Although transduction seems at the outset to be an easier task than induction, there have not been many provably useful algorithms for transduction. Moreover, the precise relation between induction and transduction has not yet been determined. The main theoretical developments related to transduction were presented by Vapnik more than twenty years ago. One of Vapnik's basic results is a rather tight error bound for transductive classification based on an exact computation of the hypergeometric tail. While tight, this bound is given implicitly via a computational routine. Our first contribution is a somewhat looser but explicit characterization of a slightly extended PAC-Bayesian version of Vapnik's transductive bound. This characterization is obtained using concentration inequalities for the tail of sums of random variables obtained by sampling without replacement. We then derive error bounds for compression schemes such as (transductive) support vector machines and for transduction algorithms based on clustering. The main observation used for deriving these new error bounds and algorithms is that the unlabeled test points, which in the transductive setting are known in advance, can be used in order to construct useful data dependent prior distributions over the hypothesis space.

A novel algorithm for actively trading stocks is presented. While traditional expert advice and "universal" algorithms (as well as standard technical trading heuristics) attempt to predict winners or trends, our approach relies on predictable statistical relations between all pairs of stocks in the market. Our empirical results on historical markets provide strong evidence that this type of technical trading can "beat the market" and moreover, can beat the best stock in the market. In doing so we utilize a new idea for smoothing critical parameters in the context of expert learning.

Inductive learning is based on inferring a general rule from a finite data set and using it to label new data. In transduction one attempts to solve the problem of using a labeled training set to label a set of unlabeled points, which are given to the learner prior to learning. Although transduction seems at the outset to be an easier task than induction, there have not been many provably useful algorithms for transduction. Moreover, the precise relation between induction and transduction has not yet been determined. The main theoretical developments related to transduction were presented by Vapnik more than twenty years ago. One of Vapnik's basic results is a rather tight error bound for transductive classification based on an exact computation of the hypergeometric tail. While tight, this bound is given implicitly via a computational routine. Our first contribution is a somewhat looser but explicit characterization of a slightly extended PAC-Bayesian version of Vapnik's transductive bound. This characterization is obtained using concentration inequalities for the tail of sums of random variables obtained by sampling without replacement. We then derive error bounds for compression schemes such as (transductive) support vector machines and for transduction algorithms based on clustering. The main observation used for deriving these new error bounds and algorithms is that the unlabeled test points, which in the transductive setting are known in advance, can be used in order to construct useful data dependent prior distributions over the hypothesis space.