Two words that are spoken in every leadership and board meeting around the world right now are "machine learning". Technology buzzwords seem to monopolize these meetings. Who could forget: digital, big data, internet of things (IoT), mobility, …-as-a-service, security, the cloud and the recent favorite, blockchain? Now, machine learning, deep learning, reinforcement learning, and numerous other technological terms that describe the artificial intelligence space have become this year's buzzwords. I've been in meetings with other executives where most people, including me, can't make heads or tails of what people are talking about when this subject comes up.

The recently proposed self-ensembling methods have achieved promising results in deep semi-supervised learning, which penalize inconsistent predictions of unlabeled data under different perturbations. However, they only consider adding perturbations to each single data point, while ignoring the connections between data samples. In this paper, we propose a novel method, called Smooth Neighbors on Teacher Graphs (SNTG). In SNTG, a graph is constructed based on the predictions of the teacher model, i.e., the implicit self-ensemble of models. Then the graph serves as a similarity measure with respect to which the representations of "similar" neighboring points are learned to be smooth on the low-dimensional manifold. We achieve state-of-the-art results on semi-supervised learning benchmarks. The error rates are 9.89%, 3.99% for CIFAR-10 with 4000 labels, SVHN with 500 labels, respectively. In particular, the improvements are significant when the labels are fewer. For the non-augmented MNIST with only 20 labels, the error rate is reduced from previous 4.81% to 1.36%. Our method also shows robustness to noisy labels.

We extract losses at two levels, at the end of the generator and at the end of the full model. The first one is a perceptual loss computed directly on the generator's outputs. This first loss ensures the GAN model is oriented towards a deblurring task. It compares the outputs of the first convolutions of VGG. The second loss is the Wasserstein loss performed on the outputs of the whole model.

Generative Adversarial Networks (GANs) are becoming popular choices for unsupervised learning. At the same time there is a concerted effort in the machine learning community to expand the range of tasks in which learning can be applied as well as to utilize methods from other disciplines to accelerate learning. With this in mind, in the current work we suggest ways to enforce given constraints in the output of a GAN both for interpolation and extrapolation. The two cases need to be treated differently. For the case of interpolation, the incorporation of constraints is built into the training of the GAN. The incorporation of the constraints respects the primary game-theoretic setup of a GAN so it can be combined with existing algorithms. However, it can exacerbate the problem of instability during training that is well-known for GANs. We suggest adding small noise to the constraints as a simple remedy that has performed well in our numerical experiments. The case of extrapolation (prediction) is more involved. First, we employ a modified interpolation training process that uses noisy data but does not necessarily enforce the constraints during training. Second, the resulting modified interpolator is used for extrapolation where the constraints are enforced after each step through projection on the space of constraints.

Generative Adversarial Networks (GANs) are a class of generative algorithms that have been shown to produce state-of-the art samples, especially in the domain of image creation. The fundamental principle of GANs is to approximate the unknown distribution of a given data set by optimizing an objective function through an adversarial game between a family of generators and a family of discriminators. In this paper, we offer a better theoretical understanding of GANs by analyzing some of their mathematical and statistical properties. We study the deep connection between the adversarial principle underlying GANs and the Jensen-Shannon divergence, together with some optimality characteristics of the problem. An analysis of the role of the discriminator family via approximation arguments is also provided. In addition, taking a statistical point of view, we study the large sample properties of the estimated distribution and prove in particular a central limit theorem. Some of our results are illustrated with simulated examples.

Generative adversarial networks (GAN) are a powerful subclass of generative models. Despite a very rich research activity leading to numerous interesting GAN algorithms, it is still very hard to assess which algorithm(s) perform better than others. We conduct a neutral, multi-faceted large-scale empirical study on state-of-the art models and evaluation measures. We find that most models can reach similar scores with enough hyperparameter optimization and random restarts. This suggests that improvements can arise from a higher computational budget and tuning more than fundamental algorithmic changes. To overcome some limitations of the current metrics, we also propose several data sets on which precision and recall can be computed. Our experimental results suggest that future GAN research should be based on more systematic and objective evaluation procedures. Finally, we did not find evidence that any of the tested algorithms consistently outperforms the original one.

Generative adversarial networks are used to generate images but still their convergence properties are not well understood. There have been a few studies who intended to investigate the stability properties of GANs as a dynamical system. This short writing can be seen in that direction. Among the proposed methods for stabilizing training of GANs, {\ss}-GAN was the first who proposed a complete annealing strategy to change high-level conditions of the GAN objective. In this note, we show by a simple example how annealing strategy works in GANs. The theoretical analysis is supported by simple simulations.

Visual events are usually accompanied by sounds in our daily lives. We pose the question: Can the machine learn the correspondence between visual scene and the sound, and localize the sound source only by observing sound and visual scene pairs like human? In this paper, we propose a novel unsupervised algorithm to address the problem of localizing the sound source in visual scenes. A two-stream network structure which handles each modality, with attention mechanism is developed for sound source localization. Moreover, although our network is formulated within the unsupervised learning framework, it can be extended to a unified architecture with a simple modification for the supervised and semi-supervised learning settings as well. Meanwhile, a new sound source dataset is developed for performance evaluation. Our empirical evaluation shows that the unsupervised method eventually go through false conclusion in some cases. We show that even with a few supervision, false conclusion is able to be corrected and the source of sound in a visual scene can be localized effectively.

Keras implementations of Generative Adversarial Networks (GANs) suggested in research papers. If dense layers produce reasonable results for a given model I will often prefer them over convolutional layers. The reason is that I would like to enable people without GPUs to test these implementations out. These models are in some cases simplified versions of the ones ultimately described in the papers, but I have chosen to focus on getting the core ideas covered instead of getting every layer configuration right. However, because of this the results will not always be as nice as in the papers.

In part one of the machine learning crash course, we introduced the field of supervised machine learning (ML) by walking through popular algorithms like linear regression and logistic regression. But supervised learning is just one of the many types of algorithms in the vast machine learning / artificial intelligence space. In this article, we take a look at two other subdisciplines: Unsupervised learning and deep learning.