Autoencoders are fundamental to creating simpler representations. In this article, we create an autoencoder with PyTorch!Continue reading on Analytics Vidhya » Source

I am sure you know Bob Ross and his program The Joy of Painting where he taught thousands of viewers how to paint beautiful landscapes with a simple and fun way, combining colors and brushstrokes, to achieve great results very quickly. Do you remember him teaching how to paint a pixel at the time? of course not! However, most of the current generative AI Art methods are still centered to teach machines how to'paint' at the pixel-level in order to achieve or mimic some painting style, e.g., GANs-based approaches and style transfer. This might be effective, but not very intuitive, specially when explaining this process to artists, who are familiar with colors and brushstrokes. At Libre AI, we have started a Creative AI initiative with the goal to make more accessible the advances of AI to groups of artists who do not necessarily have a tech background.

Driven by the increasingly larger deep learning models, neural language generation (NLG) has enjoyed unprecedentedly improvement and is now able to generate a diversity of human-like texts on demand, granting itself the capability of serving as a human writing assistant. Text attribute transfer is one of the most important NLG tasks, which aims to control certain attributes that people may expect the texts to possess, such as sentiment, tense, emotion, political position, etc. It has a long history in Natural Language Processing but recently gains much more attention thanks to the promising performance brought by deep learning models. In this article, we present a systematic survey on these works for neural text attribute transfer. We collect all related academic works since the first appearance in 2017. We then select, summarize, discuss, and analyze around 65 representative works in a comprehensive way. Overall, we have covered the task formulation, existing datasets and metrics for model development and evaluation, and all methods developed over the last several years. We reveal that existing methods are indeed based on a combination of several loss functions with each of which serving a certain goal. Such a unique perspective we provide could shed light on the design of new methods. We conclude our survey with a discussion on open issues that need to be resolved for better future development.

The classification of DNA sequences is a key research area in bioinformatics as it enables researchers to conduct genomic analysis and detect possible diseases. In this paper, three state-of-the-art algorithms, namely Convolutional Neural Networks, Deep Neural Networks, and N-gram Probabilistic Models, are used for the task of DNA classification. Furthermore, we introduce a novel feature extraction method based on the Levenshtein distance and randomly generated DNA sub-sequences to compute information-rich features from the DNA sequences. We also use an existing feature extraction method based on 3-grams to represent amino acids and combine both feature extraction methods with a multitude of machine learning algorithms. Four different data sets, each concerning viral diseases such as Covid-19, AIDS, Influenza, and Hepatitis C, are used for evaluating the different approaches. The results of the experiments show that all methods obtain high accuracies on the different DNA datasets. Furthermore, the domain-specific 3-gram feature extraction method leads in general to the best results in the experiments, while the newly proposed technique outperforms all other methods on the smallest Covid-19 dataset

Recently, a provocative claim was published that number sense spontaneously emerges in a deep neural network trained merely for visual object recognition. This has, if true, far reaching significance to the fields of machine learning and cognitive science alike. In this paper, we prove the above claim to be unfortunately incorrect. The statistical analysis to support the claim is flawed in that the sample set used to identify number-aware neurons is too small, compared to the huge number of neurons in the object recognition network. By this flawed analysis one could mistakenly identify number-sensing neurons in any randomly initialized deep neural networks that are not trained at all. With the above critique we ask the question what if a deep convolutional neural network is carefully trained for numerosity? Our findings are mixed. Even after being trained with number-depicting images, the deep learning approach still has difficulties to acquire the abstract concept of numbers, a cognitive task that preschoolers perform with ease. But on the other hand, we do find some encouraging evidences suggesting that deep neural networks are more robust to distribution shift for small numbers than for large numbers.

With recent advancements in deep learning and the availability of huge amount of data, data-driven prediction in time series has attracted more and more attention. Specifically, traffic forecasting is the key component of a transportation system powered by artificial intelligence[2] [5]. Traditionally, time series forecasting includes methods such as K-nearest Neighbor (KNN), Support Vector Regression (SVR), etc [6]. This paper proposes the stacked LSTM model to capture the complex temporal patterns. The main contributions include: - Analyzing real traffic volume data in Toronto downtown area - Proposing the stacked LSTM model with substantial gain comparing to the baseline model - Improving the model performance with a comprehensive set of training methodologies Deep learning has been widely adopted in time series forecasting[5]. One category is time series classification which assigns predefined class labels to time series output.

Instrumental variable (IV) regression is a standard strategy for learning causal relationships between confounded treatment and outcome variables from observational data by utilizing an instrumental variable, which affects the outcome only through the treatment. In classical IV regression, learning proceeds in two stages: stage 1 performs linear regression from the instrument to the treatment; and stage 2 performs linear regression from the treatment to the outcome, conditioned on the instrument. We propose a novel method, deep feature instrumental variable regression (DFIV), to address the case where relations between instruments, treatments, and outcomes may be nonlinear. In this case, deep neural nets are trained to define informative nonlinear features on the instruments and treatments. We propose an alternating training regime for these features to ensure good end-to-end performance when composing stages 1 and 2, thus obtaining highly flexible feature maps in a computationally efficient manner. DFIV outperforms recent state-of-the-art methods on challenging IV benchmarks, including settings involving high dimensional image data. DFIV also exhibits competitive performance in off-policy policy evaluation for reinforcement learning, which can be understood as an IV regression task.

Ordinary (pointwise) binary classification aims to learn a binary classifier from pointwise labeled data. However, such pointwise labels may not be directly accessible due to privacy, confidentiality, or security considerations. In this case, can we still learn an accurate binary classifier? This paper proposes a novel setting, namely pairwise comparison (Pcomp) classification, where we are given only pairs of unlabeled data that we know one is more likely to be positive than the other, instead of pointwise labeled data. Pcomp classification is useful for private or subjective classification tasks. To solve this problem, we present a mathematical formulation for the generation process of pairwise comparison data, based on which we exploit an unbiased risk estimator (URE) to train a binary classifier by empirical risk minimization and establish an estimation error bound. We first prove that a URE can be derived and improve it using correction functions. Then, we start from the noisy-label learning perspective to introduce a progressive URE and improve it by imposing consistency regularization. Finally, experiments validate the effectiveness of our proposed solutions for Pcomp classification.

Continual learning systems will interact with humans, with each other, and with the physical world through time -- and continue to learn and adapt as they do. An important open problem for continual learning is a large-scale benchmark that enables realistic evaluation of algorithms. In this paper, we study a natural setting for continual learning on a massive scale. We introduce the problem of personalized online language learning (POLL), which involves fitting personalized language models to a population of users that evolves over time. To facilitate research on POLL, we collect massive datasets of Twitter posts. These datasets, Firehose10M and Firehose100M, comprise 100 million tweets, posted by one million users over six years. Enabled by the Firehose datasets, we present a rigorous evaluation of continual learning algorithms on an unprecedented scale. Based on this analysis, we develop a simple algorithm for continual gradient descent (ConGraD) that outperforms prior continual learning methods on the Firehose datasets as well as earlier benchmarks. Collectively, the POLL problem setting, the Firehose datasets, and the ConGraD algorithm enable a complete benchmark for reproducible research on web-scale continual learning.

Solar magnetic fields play a key role in understanding the nature of the coronal phenomena. Global coronal magnetic fields are usually extrapolated from photospheric fields, for which farside data is taken when it was at the frontside, about two weeks earlier. For the first time we have constructed the extrapolations of global magnetic fields using frontside and artificial intelligence (AI)-generated farside magnetic fields at a near-real time basis. We generate the farside magnetograms from three channel farside observations of Solar Terrestrial Relations Observatory (STEREO) Ahead (A) and Behind (B) by our deep learning model trained with frontside Solar Dynamics Observatory extreme ultraviolet images and magnetograms. For frontside testing data sets, we demonstrate that the generated magnetic field distributions are consistent with the real ones; not only active regions (ARs), but also quiet regions of the Sun. We make global magnetic field synchronic maps in which conventional farside data are replaced by farside ones generated by our model. The synchronic maps show much better not only the appearance of ARs but also the disappearance of others on the solar surface than before. We use these synchronized magnetic data to extrapolate the global coronal fields using Potential Field Source Surface (PFSS) model. We show that our results are much more consistent with coronal observations than those of the conventional method in view of solar active regions and coronal holes. We present several positive prospects of our new methodology for the study of solar corona, heliosphere, and space weather.