The automatic analysis of ultrasound sequences can substantially improve the efficiency of clinical diagnosis. In this work we present our attempt to automate the challenging task of measuring the vascular diameter of the fetal abdominal aorta from ultrasound images. We propose a neural network architecture consisting of three blocks: a convolutional layer for the extraction of imaging features, a Convolution Gated Recurrent Unit (C-GRU) for enforcing the temporal coherence across video frames and exploiting the temporal redundancy of a signal, and a regularized loss function, called \textit{CyclicLoss}, to impose our prior knowledge about the periodicity of the observed signal. We present experimental evidence suggesting that the proposed architecture can reach an accuracy substantially superior to previously proposed methods, providing an average reduction of the mean squared error from $0.31 mm^2$ (state-of-art) to $0.09 mm^2$, and a relative error reduction from $8.1\%$ to $5.3\%$. The mean execution speed of the proposed approach of 289 frames per second makes it suitable for real time clinical use.

Raven's Progressive Matrices are one of the widely used tests in evaluating the human test taker's fluid intelligence. Analogously, this paper introduces geometric generalization based zero-shot learning tests to measure the rapid learning ability and the internal consistency of deep generative models. Our empirical research analysis on state-of-the-art generative models discern their ability to generalize concepts across classes. In the process, we introduce Infinite World, an evaluable, scalable, multi-modal, light-weight dataset and Zero-Shot Intelligence Metric ZSI. The proposed tests condenses human-level spatial and numerical reasoning tasks to its simplistic geometric forms. The dataset is scalable to a theoretical limit of infinity, in numerical features of the generated geometric figures, image size and in quantity. We systematically analyze state-of-the-art model's internal consistency, identify their bottlenecks and propose a pro-active optimization method for few-shot and zero-shot learning.

Motivated by applications in Game Theory, Optimization, and Generative Adversarial Networks, recent work of Daskalakis et al. and Liang and Stokes has established that a variant of the widely used Gradient Descent/Ascent procedure, called "Optimistic Gradient Descent/Ascent (OGDA)", exhibits last-iterate convergence to saddle points in {\em unconstrained} convex-concave min-max optimization problems. We show that the same holds true in the more general problem of {\em constrained} min-max optimization under a variant of the Multiplicative-Weights-Update method called "Optimistic Multiplicative-Weights Update (OMWU)". The generality of the constrained problem, which in particular captures all Linear Programming, requires fundamentally different techniques for analyzing the progress of OMWU towards min-max solutions. We show that OMWU monotonically improves the Kullback-Leibler divergence of the current iterate to the (appropriately normalized) min-max solution until it enters a neighborhood of the solution. Inside that neighborhood we show that OMWU becomes a contracting map converging to the exact solution. We experiment with zero-sum games to measure how the convergence rate scales with the dimension.

Abstract--While we are usually focused on predicting future values of time series, it is often valuable to additionally predict their entire probability distributions, for example to evaluate risk or Monte Carlo simulations. On example of time series of 30000 Dow Jones Industrial Averages, there will be shown application of hierarchical correlation reconstruction for this purpose: mean-square fitting polynomial as joint density for (current value, context), where context is for example a few previous values. Then substituting the currently observed context and normalizing density to 1, we get predicted probability distribution for the current value. In contrast to standard machine learning approaches like neural networks, optimal coefficients here can be inexpensively directly calculated, are unique and independent, each has a specific cumulant-like interpretation, and such approximation can approach complete description of any joint distribution - providing a perfect tool to quantitatively describe and exploit statistical dependencies in time series. Modeling spatial or temporal correlation between observed values is a difficult task required in a countless number of applications.

In this work we offer a framework for reasoning about a wide class of existing objectives in machine learning. We develop a formal correspondence between this work and thermodynamics and discuss its implications.

In training a deep learning system to perform audio transcription, two practical problems may arise. Firstly, most datasets are weakly labelled, having only a list of events present in each recording without any temporal information for training. Secondly, deep neural networks need a very large amount of labelled training data to achieve good quality performance, yet in practice it is difficult to collect enough samples for most classes of interest. In this paper, we propose factorising the final task of audio transcription into multiple intermediate tasks in order to improve the training performance when dealing with this kind of low-resource datasets. We evaluate three data-efficient approaches of training a stacked convolutional and recurrent neural network for the intermediate tasks. Our results show that different methods of training have different advantages and disadvantages.

Although sometimes default values exist, there is no agreed upon principle for their definition (but see our recent work in in (Probst et al., 2018) for a potential approach). Automatic tuning of such parameters is a possible solution (Claesen and Moor, 2015), but comes with a considerable computational burden. Meta-learning tries to decrease this cost (Feurer et al., 2015), by reusing information of previous runs of the algorithm on similar datasets, which obviously requires access to such prior empirical results. With this paper we provide a freely accessible meta dataset that contains around 2.5 million runs of six different machine learning algorithms on 38 classification datasets. Large, freely available datasets like Imagenet (Deng et al., 2009) are important for the progress of machine learning, we hope to support developments in the area of meta-learning and benchmarking, meta-learning and hyperparameter tuning with our work here. While similar meta-datasets have been created in the past, we were not able to access them by the links provided in their respective papers: Smith et al. (2014) provides a repository with Weka-based machine learning experiments on 72 data sets, 9 machine learning algorithms, 10 hyperparameter settings for each algorithm, and several meta-features of each data set. Reif (2012) created a meta-dataset based on machine learning experiments on 83 datasets, 6 classification algorithms, and 49 meta features. In this paper, we describe our experimental setup, to specify how our meta-dataset is created by running random machine learning experiments through the OpenML platform (Vanschoren et al., 2013) and how to access our results.

In acoustic scene classification researches, audio segment is usually split into multiple samples. Majority voting is then utilized to ensemble the results of the samples. In this paper, we propose a punishment voting algorithm based on the super categories construction method for acoustic scene classification. Specifically, we propose a DenseNet-like model as the base classifier. The base classifier is trained by the CQT spectrograms generated from the raw audio segments. Taking advantage of the results of the base classifier, we propose a super categories construction method using the spectral clustering. Super classifiers corresponding to the constructed super categories are further trained. Finally, the super classifiers are utilized to enhance the majority voting of the base classifier by punishment voting. Experiments show that the punishment voting obviously improves the performances on both the DCASE2017 Development dataset and the LITIS Rouen dataset.

Whether neural networks can learn abstract reasoning or whether they merely rely on superficial statistics is a topic of recent debate. Here, we propose a dataset and challenge designed to probe abstract reasoning, inspired by a well-known human IQ test. To succeed at this challenge, models must cope with various generalisation `regimes' in which the training and test data differ in clearly-defined ways. We show that popular models such as ResNets perform poorly, even when the training and test sets differ only minimally, and we present a novel architecture, with a structure designed to encourage reasoning, that does significantly better. When we vary the way in which the test questions and training data differ, we find that our model is notably proficient at certain forms of generalisation, but notably weak at others. We further show that the model's ability to generalise improves markedly if it is trained to predict symbolic explanations for its answers. Altogether, we introduce and explore ways to both measure and induce stronger abstract reasoning in neural networks. Our freely-available dataset should motivate further progress in this direction.

We propose a novel end-to-end neural network architecture that, once trained, directly outputs a probabilistic clustering of a batch of input examples in one pass. It estimates a distribution over the number of clusters $k$, and for each $1 \leq k \leq k_\mathrm{max}$, a distribution over the individual cluster assignment for each data point. The network is trained in advance in a supervised fashion on separate data to learn grouping by any perceptual similarity criterion based on pairwise labels (same/different group). It can then be applied to different data containing different groups. We demonstrate promising performance on high-dimensional data like images (COIL-100) and speech (TIMIT). We call this ``learning to cluster'' and show its conceptual difference to deep metric learning, semi-supervise clustering and other related approaches while having the advantage of performing learnable clustering fully end-to-end.