The increasingly fast development cycle for online course contents, along with the diverse student demographics in each online classroom, make real-time student outcomes prediction an interesting topic for both industrial research and practical needs. In this paper, we tackle the problem of real-time student performance prediction in an on-going course using a domain adaptation framework. This framework is a system trained on labeled student outcome data from previous coursework but is meant to be deployed on another course. In particular, we introduce a GritNet architecture, and develop an unsupervised domain adaptation method to transfer a GritNet trained on a past course to a new course without any student outcome label. Our results for real Udacity student graduation predictions show that the GritNet not only generalizes well from one course to another across different Nanodegree programs, but also enhances real-time predictions explicitly in the first few weeks when accurate predictions are most challenging.

As different layouts can characterize different aspects of the same graph, finding a "good" layout of a graph is an important task for graph visualization. In practice, users often visualize a graph in multiple layouts by using different methods and varying parameter settings until they find a layout that best suits the purpose of the visualization. However, this trial-and-error process is often haphazard and time-consuming. To provide users with an intuitive way to navigate the layout design space, we present a technique to systematically visualize a graph in diverse layouts using deep generative models. We design an encoder-decoder architecture to learn a model from a collection of example layouts, where the encoder represents training examples in a latent space and the decoder produces layouts from the latent space. In particular, we train the model to construct a two-dimensional latent space for users to easily explore and generate various layouts. We demonstrate our approach through quantitative and qualitative evaluations of the generated layouts. The results of our evaluations show that our model is capable of learning and generalizing abstract concepts of graph layouts, not just memorizing the training examples. In summary, this paper presents a fundamentally new approach to graph visualization where a machine learning model learns to visualize a graph from examples without manually-defined heuristics.

Electronic records contain sequences of events, some of which take place all at once in a single visit, and others that are dispersed over multiple visits, each with a different timestamp. We postulate that fine temporal detail, e.g., whether a series of blood tests are completed at once or in rapid succession should not alter predictions based on this data. Motivated by this intuition, we propose models for analyzing sequences of multivariate clinical time series data that are invariant to this temporal clustering. We propose an efficient data augmentation technique that exploits the postulated temporal-clustering invariance to regularize deep neural networks optimized for several clinical prediction tasks. We introduce two techniques to temporally coarsen (downsample) irregular time series: (i) grouping the data points based on regularly-spaced timestamps; and (ii) clustering them, yielding irregularly-paced timestamps. Moreover, we propose a MultiResolution Ensemble (MRE) model, improving predictive accuracy by ensembling predictions based on inputs sequences transformed by different coarsening operators. Our experiments show that MRE improves the mAP on the benchmark mortality prediction task from 51.53% to 53.92%.

One way to interpret trained deep neural networks (DNNs) is by inspecting characteristics that neurons in the model respond to, such as by iteratively optimising the model input (e.g., an image) to maximally activate specific neurons. However, this requires a careful selection of hyper-parameters to generate interpretable examples for each neuron of interest, and current methods rely on a manual, qualitative evaluation of each setting, which is prohibitively slow. We introduce a new metric that uses Fr\'echet Inception Distance (FID) to encourage similarity between model activations for real and generated data. This provides an efficient way to evaluate a set of generated examples for each setting of hyper-parameters. We also propose a novel GAN-based method for generating explanations that enables an efficient search through the input space and imposes a strong prior favouring realistic outputs. We apply our approach to a classification model trained to predict whether a music audio recording contains singing voice. Our results suggest that this proposed metric successfully selects hyper-parameters leading to interpretable examples, avoiding the need for manual evaluation. Moreover, we see that examples synthesised to maximise or minimise the predicted probability of singing voice presence exhibit vocal or non-vocal characteristics, respectively, suggesting that our approach is able to generate suitable explanations for understanding concepts learned by a neural network.

Magnetic resonance imaging (MRI) is being increasingly utilized to assess, diagnose, and plan treatment for a variety of diseases. The ability to visualize tissue in varied contrasts in the form of MR pulse sequences in a single scan provides valuable insights to physicians, as well as enabling automated systems performing downstream analysis. However many issues like prohibitive scan time, image corruption, different acquisition protocols, or allergies to certain contrast materials may hinder the process of acquiring multiple sequences for a patient. This poses challenges to both physicians and automated systems since complementary information provided by the missing sequences is lost. In this paper, we propose a variant of generative adversarial network (GAN) capable of leveraging redundant information contained within multiple available sequences in order to generate one or more missing sequences for a patient scan. The proposed network is designed as a multi-input, multi-output network which combines information from all the available pulse sequences, implicitly infers which sequences are missing, and synthesizes the missing ones in a single forward pass. We demonstrate and validate our method on two brain MRI datasets each with four sequences, and show the applicability of the proposed method in simultaneously synthesizing all missing sequences in any possible scenario where either one, two, or three of the four sequences may be missing. We compare our approach with competing unimodal and multi-modal methods, and show that we outperform both quantitatively and qualitatively.

Apprenticeship has a long history in art -- and now a painting AI will join the ranks of those who have honed their skills by imitating the masterpieces of other artists. Much like the pupils of the old masters, the new AI meticulously studies the work of virtuoso painters like Vermeer and Van Gogh and learns to reproduce their works. The arty algorithm uses deep learning techniques to master the way that each artist lays their brushstrokes on the canvas, mimicking stroke colour, density and size. Once adept at a given approach, the AI can then make new works of art in the learnt style based on photographs given to it. The algorithm, dubbed'PaintBot', is the creation of a team of researchers from the University of Maryland, the ByteDance AI Lab and Adobe Research.

Artificial intelligence is enabling many scientific breakthroughs, especially in fields of study that generate high volumes of complex data such as neuroscience. As impossible as it may seem, neuroscientists are making strides in decoding neural activity into speech using artificial neural networks. Yesterday, the neuroscience team of Gopala K. Anumanchipalli, Josh Chartier, and Edward F. Chang of University of California San Francisco (UCSF) published in Nature their study using artificial intelligence and a state-of-the-art brain-machine interface to produce synthetic speech from brain recordings. The concept is relatively straightforward--record the brain activity and audio of participants while they are reading aloud in order to create a system that decodes brain signals for vocal tract movements, then synthesize speech from the decoded movements. The execution of the concept required sophisticated finessing of cutting-edge AI techniques and tools.

Neural networks are changing the way that Lex Flagel studies DNA. Lex's recent paper – The Unreasonable Effectiveness of Convolutional Neural Networks in Population Genetic Inference – demonstrates how simple deep learning techniques can be used to tackle the ever-changing field of DNA research. Lex is the Quantitative Genetics Team Lead at Bayer Crop Science. At Bayer, Lex focuses on genetics, genomics, bioinformatics, and data science on crops like corn and soybeans. Don't worry -- we'll dig into what all those terms mean! Lex has a PhD in Genetics from Iowa State University. I'm excited to share my conversation with Lex for this Humans of Machine Learning (#humansofml) interview. In this post, we're going to learn about how Lex uses deep learning to study population genetics, as well as Lex's own journey with data science and AI.

Chinese named entity recognition (CNER) is an important task in Chinese natural language processing field. However, CNER is very challenging since Chinese entity names are highly context-dependent. In addition, Chinese texts lack delimiters to separate words, making it difficult to identify the boundary of entities. Besides, the training data for CNER in many domains is usually insufficient, and annotating enough training data for CNER is very expensive and time-consuming. In this paper, we propose a neural approach for CNER. First, we introduce a CNN-LSTM-CRF neural architecture to capture both local and long-distance contexts for CNER. Second, we propose a unified framework to jointly train CNER and word segmentation models in order to enhance the ability of CNER model in identifying entity boundaries. Third, we introduce an automatic method to generate pseudo labeled samples from existing labeled data which can enrich the training data. Experiments on two benchmark datasets show that our approach can effectively improve the performance of Chinese named entity recognition, especially when training data is insufficient.

Deep learning based knowledge tracing model has been shown to outperform traditional knowledge tracing model without the need for human-engineered features, yet its parameters and representations have long been criticized for not being explainable. In this paper, we propose Deep-IRT which is a synthesis of the item response theory (IRT) model and a knowledge tracing model that is based on the deep neural network architecture called dynamic key-value memory network (DKVMN) to make deep learning based knowledge tracing explainable. Specifically, we use the DKVMN model to process the student's learning trajectory and estimate the student ability level and the item difficulty level over time. Then, we use the IRT model to estimate the probability that a student will answer an item correctly using the estimated student ability and the item difficulty. Experiments show that the Deep-IRT model retains the performance of the DKVMN model, while it provides a direct psychological interpretation of both students and items.