With the explosion of massive, widely available unlabeled data in the past years, finding label and time efficient, robust learning algorithms has become ever more important in theory and in practice. We study the paradigm of active learning, in which algorithms with access to large pools of data may adaptively choose what samples to label in the hope of exponentially increasing efficiency. By introducing comparisons, an additional type of query comparing two points, we provide the first time and query efficient algorithms for learning non-homogeneous linear separators robust to bounded (Massart) noise. We further provide algorithms for a generalization of the popular Tsybakov low noise condition, and show how comparisons provide a strong reliability guarantee that is often impractical or impossible with only labels - returning a classifier that makes no errors with high probability.

Semi-supervised learning aims to take advantage of a large amount of unlabeled data to improve the accuracy of a model that only has access to a small number of labeled examples. We propose curriculum labeling, an approach that exploits pseudo-labeling for propagating labels to unlabeled samples in an iterative and self-paced fashion. This approach is surprisingly simple and effective and surpasses or is comparable with the best methods proposed in the recent literature across all the standard benchmarks for image classification. Notably, we obtain 94.91% accuracy on CIFAR-10 using only 4,000 labeled samples, and 88.56% top-5 accuracy on Imagenet-ILSVRC using 128,000 labeled samples. In contrast to prior works, our approach shows improvements even in a more realistic scenario that leverages out-of-distribution unlabeled data samples.

-- Generative Adversarial Networks (GANs) have demonstrated their ability to learn patterns in data and produce new exemplars similar to, but different from, their training set in several domains, including video games. However, GANs have a fixed output size, so creating levels of arbitrary size for a dungeon crawling game is difficult. GANs also have trouble encoding semantic requirements that make levels interesting and playable. This paper combines a GAN approach to generating individual rooms with a graph grammar approach to combining rooms into a dungeon. The GAN captures design principles of individual rooms, but the graph grammar organizes rooms into a global layout with a sequence of obstacles determined by a designer . Room data from The Legend of Zelda is used to train the GAN. This approach is validated by a user study, showing that GAN dungeons are as enjoyable to play as a level from the original game, and levels generated with a graph grammar alone. However, GAN dungeons have rooms considered more complex, and plain graph grammar's dungeons are considered least complex and challenging. Only the GAN approach creates an extensive supply of both layouts and rooms, where rooms span across the spectrum of those seen in the training set to new creations merging design principles from multiple rooms. Video game developers increase replayability and reduce costs using Procedural Content Generation (PCG [1]). Instead of experiencing the game once, players see new variations on every playthrough. This concept was introduced in Rouge (1980), which procedurally generates new dungeons on every play. PCG is also applied to modern games like Minecraft (2009), where users play on generated landscapes, and No Man's Sky (2016), where procedurally generated worlds contain procedurally generated animals. PCG encourages increased exploration and increases replayability. An emerging PCG technique is Generative Adversarial Networks (GANs [2]) used to search the latent design space of video game levels, as has been done in Super Mario Bros. [3], Doom [4], an educational game [5], and the General Video Game AI (GVG-AI [6]) adaptation of The Legend of Zelda [7].

A BSTRACT This paper describes a new form of unsupervised learning, whose input is a set of unlabeled points that are assumed to be local maxima of an unknown value function v in an unknown subset of the vector space. Two functions are learned: (i) a set indicator c, which is a binary classifier, and (ii) a comparator function h that given two nearby samples, predicts which sample has the higher value of the unknown function v . Loss terms are used to ensure that all training samples x are a local maxima of v, according to h and satisfy c( x) 1 . Therefore, c and h provide training signals to each other: a point x null in the vicinity of x satisfies c (x) 1 or is deemed by h to be lower in value than x . We present an algorithm, show an example where it is more efficient to use local maxima as an indicator function than to employ conventional classification, and derive a suitable generalization bound. Our experiments show that the method is able to outperform one-class classification algorithms in the task of anomaly detection and also provide an additional signal that is extracted in a completely unsupervised way. 1 I NTRODUCTION ...from so simple a beginning endless forms most beautiful and most wonderful have been, and are being, evolved. We do not observe the even larger quantity of less spectacular forms and we cannot see those forms that are incompatible with existence. In other words, each sample we observe is the result of optimizing some fitness or value function under a set of constraints: the alternative, lower-value, samples are removed and the samples that do not satisfy the constraints are also missing. The same principle also holds at the sub-cellular level. For example, a gene can have many forms. Some of them are completely synonymous, while others are viable alternatives. The gene forms that become most frequent are those which are not only viable, but which also minimize the energetic cost of their expression (Farkas et al., 2018). For example, the genes that encode proteins comprised of amino acids of higher availability or that require lower expression levels to achieve the same outcome have an advantage.

Compared to supervised learning, semi-supervised learning reduces the dependence of deep learning on a large number of labeled samples. In this work, we use a small number of labeled samples and perform data augmentation on unlabeled samples to achieve image classification. Our method constrains all samples to the predefined evenly-distributed class centroids (PEDCC) by the corresponding loss function. Specifically, the PEDCC-Loss for labeled samples, and the maximum mean discrepancy loss for unlabeled samples are used to make the feature distribution closer to the distribution of PEDCC. Our method ensures that the inter-class distance is large and the intra-class distance is small enough to make the classification boundaries between different classes clearer. Meanwhile, for unlabeled samples, we also use KL divergence to constrain the consistency of the network predictions between unlabeled and augmented samples. Our semi-supervised learning method achieves the state-of-the-art results, with 4000 labeled samples on CIFAR10 and 1000 labeled samples on SVHN, and the accuracy is 95.10% and 97.58% respectively.

Machine Learning and Artificial Intelligence are rapidly changing the landscape of how organizations function in the world. From data analysis to make independent decisions based upon past experiences, Machine Learning is being used to help organizations make informed decisions but before any of that happens, the algorithms and associated software have to be trained accordingly. Two methods namely supervised learning and unsupervised learning, are widely used to train AI programs. Supervised Learning can be considered equivalent to teaching a toddler how to walk or so forth. The software will have a dataset as well as corresponding input and output pairs which can form a training model for the software. Linear Regression is an example of Supervised Learning and in this case, regression is used when the output is a real number or quantity, let's say dollars or weights.

This paper addresses the problem of manipulating images using natural language description. Our task aims to semantically modify visual attributes of an object in an image according to the text describing the new visual appearance. Although existing methods synthesize images having new attributes, they do not fully preserve text-irrelevant contents of the original image. In this paper, we propose the text-adaptive generative adversarial network (TAGAN) to generate semantically manipulated images while preserving text-irrelevant contents. The key to our method is the text-adaptive discriminator that creates word level local discriminators according to input text to classify fine-grained attributes independently.

Semi-supervised learning is a classification method which makes use of both labeled data and unlabeled data for training. In this paper, we propose a semi-supervised learning algorithm using a Bayesian semi-supervised model. We make a general assumption that the observations will follow two multivariate normal distributions depending on their true labels after the same unknown transformation. We use B-splines to put a prior on the transformation function for each component. To use unlabeled data in a semi-supervised setting, we assume the labels are missing at random. The posterior distributions can then be described using our assumptions, which we compute by the Gibbs sampling technique. The proposed method is then compared with several other available methods through an extensive simulation study. Finally we apply the proposed method in real data contexts for diagnosing breast cancer and classify radar returns. We conclude that the proposed method has better prediction accuracy in a wide variety of cases.

Supervised learning models, also known as quantitative structure-activity regression (QSAR) models, are increasingly used in assisting the process of preclinical, small molecule drug discovery. The models are trained on data consisting of a finite dimensional representation of molecular structures and their corresponding target specific activities. These models can then be used to predict the activity of previously unmeasured novel compounds. In this work we address two problems related to this approach. The first is to estimate the extent to which the quality of the model predictions degrades for compounds very different from the compounds in the training data. The second is to adjust for the screening dependent selection bias inherent in many training data sets. In the most extreme cases, only compounds which pass an activity-dependent screening are reported. By using a semi-supervised learning framework, we show that it is possible to make predictions which take into account the similarity of the testing compounds to those in the training data and adjust for the reporting selection bias. We illustrate this approach using publicly available structure-activity data on a large set of compounds reported by GlaxoSmithKline (the Tres Cantos AntiMalarial Set) to inhibit in vitro P. falciparum growth.

--There has been a growing concern about the fairness of decision-making systems based on machine learning. The shortage of labeled data has been always a challenging problem facing machine learning based systems. In such scenarios, semi-supervised learning has shown to be an effective way of exploiting unlabeled data to improve upon the performance of model. Notably, unlabeled data do not contain label information which itself can be a significant source of bias in training machine learning systems. This inspired us to tackle the challenge of fairness by formulating the problem in a semi-supervised framework. In this paper, we propose a semi-supervised algorithm using neural networks benefiting from unlabeled data to not just improve the performance but also improve the fairness of the decision-making process. The proposed model, called SSFair, exploits the information in the unlabeled data to mitigate the bias in the training data.