Running a Python script for a few hours just to find out its results are useless – feels bad. Many software domains have long-running processes that need to be monitored, but machine learning's requirements are a bit different. Monitoring machine learning requires live netrics but also comparing metrics after the process died. Alongside that, users need to see the metrics visually in charts to identify trends. This post will expand on these differences and explore the most popular strategies for monitoring a model training session using Python.

The goal is to detect the OOD cases with limited in-domain (ID) training data, since we observe that training data is often insufficient in machine learning applications. In this work, we propose an OOD-resistant Prototypical Network to tackle this zero-shot OOD detection and few-shot ID classification task. Evaluation on real-world datasets show that the proposed solution outperforms state-of-the-art methods in zero-shot OOD detection task, while maintaining a competitive performance on ID classification task. 1 Introduction Text classification tasks in real-world applications often consists of 2 components-In-Doman (ID) classification and Out-of-Domain (OOD) detection components (Liao et al., 2018; Kim and Kim, 2018; Shu et al., 2017; Shamekhi et al., 2018). ID classification refers to classifying a user's input with a label that exists in the training data, and OOD detection refers to designate a special OOD tag to the input when it does not belong to any of the labels in the ID training dataset (Dai et al., 2007). Recent state-of-the-art deep learning (DL) approaches for OOD detection and ID classification task often require massive amounts of ID or OOD labeled data (Kim and Kim, 2018).

Molecule property prediction is a fundamental problem for computer-aided drug discovery and materials science. Quantum-chemical simulations such as density functional theory (DFT) have been widely used for calculating the molecule properties, however, because of the heavy computational cost, it is difficult to search a huge number of potential chemical compounds. Machine learning methods for molecular modeling are attractive alternatives, however, the development of expressive, accurate, and scalable graph neural networks for learning molecular representations is still challenging. In this work, we propose a simple and powerful graph neural networks for molecular property prediction. We model a molecular as a directed complete graph in which each atom has a spatial position, and introduce a recursive neural network with simple gating function. We also feed input embeddings for every layers as skip connections to accelerate the training. Experimental results show that our model achieves the state-of-the-art performance on the standard benchmark dataset for molecular property prediction.

Cancer is a complex disease, the understanding and treatment of which are being aided through increases in the volume of collected data and in the scale of deployed computing power. Consequently, there is a growing need for the development of data-driven and, in particular, deep learning methods for various tasks such as cancer diagnosis, detection, prognosis, and prediction. Despite recent successes, however, designing high-performing deep learning models for nonimage and nontext cancer data is a time-consuming, trial-and-error, manual task that requires both cancer domain and deep learning expertise. To that end, we develop a reinforcement-learning-based neural architecture search to automate deep-learning-based predictive model development for a class of representative cancer data. We develop custom building blocks that allow domain experts to incorporate the cancer-data-specific characteristics. We show that our approach discovers deep neural network architectures that have significantly fewer trainable parameters, shorter training time, and accuracy similar to or higher than those of manually designed architectures. We study and demonstrate the scalability of our approach on up to 1,024 Intel Knights Landing nodes of the Theta supercomputer at the Argonne Leadership Computing Facility.

Crohn's disease, one of two inflammatory bowel diseases (IBD), affects 200,000 people in the UK alone, or roughly one in every 500. We explore the feasibility of deep learning algorithms for identification of terminal ileal Crohn's disease in Magnetic Resonance Enterography images on a small dataset. We show that they provide comparable performance to the current clinical standard, the MaRIA score, while requiring only a fraction of the preparation and inference time. Moreover, bowels are subject to high variation between individuals due to the complex and free-moving anatomy. Thus we also explore the effect of difficulty of the classification at hand on performance. Finally, we employ soft attention mechanisms to amplify salient local features and add interpretability.

In this work, we focus on the task of Automatic Question Generation (AQG) where given a passage and an answer the task is to generate the corresponding question. It is desired that the generated question should be (i) grammatically correct (ii) answerable from the passage and (iii) specific to the given answer. An analysis of existing AQG models shows that they produce questions which do not adhere to one or more of {the above-mentioned qualities}. In particular, the generated questions look like an incomplete draft of the desired question with a clear scope for refinement. {To alleviate this shortcoming}, we propose a method which tries to mimic the human process of generating questions by first creating an initial draft and then refining it. More specifically, we propose Refine Network (RefNet) which contains two decoders. The second decoder uses a dual attention network which pays attention to both (i) the original passage and (ii) the question (initial draft) generated by the first decoder. In effect, it refines the question generated by the first decoder, thereby making it more correct and complete. We evaluate RefNet on three datasets, \textit{viz.}, SQuAD, HOTPOT-QA, and DROP, and show that it outperforms existing state-of-the-art methods by 7-16\% on all of these datasets. Lastly, we show that we can improve the quality of the second decoder on specific metrics, such as, fluency and answerability by explicitly rewarding revisions that improve on the corresponding metric during training. The code has been made publicly available \footnote{https://github.com/PrekshaNema25/RefNet-QG}

Recent efforts have shown promising results for person re-identification by designing part-based architectures to allow a neural network to learn discriminative representations from semantically coherent parts. Some efforts use soft attention to reallocate distant outliers to their most similar parts, while others adjust part granularity to incorporate more distant positions for learning the relationships. Others seek to generalize part-based methods by introducing a dropout mechanism on consecutive regions of the feature map to enhance distant region relationships. In this paper, we propose a novel attention mechanism to directly model long-range relationships via second-order feature statistics. When combined with a generalized DropBlock module, our method performs equally to or better than state-of-the-art results for mainstream person re-identification datasets, including Market1501, CUHK03, and DukeMTMC-reID. 1. Introduction Person re-identification (re-ID) is an essential component of intelligent surveillance systems, which draws increasing interest from the computer vision community. It is challenging to associate multiple images captured by cameras with non-overlapping viewpoints with the same person-of-interest. Specifically, this task is challenging due to the dramatic variations with respect to illumination, occlusion, resolution, human pose, view angle, clothing, and background. The person re-ID research community has proposed various effective handcrafted features [2, 20, 26, 28, 24, 6, 21, 25] to address these challenges. Methods based on deep convolutional networks have also been introduced to learn discriminative features and representations that are robust to these variations, thereby pushing multiple re-ID benchmarks to a whole new level.

Classical Chinese poetry is a jewel in the treasure house of Chinese culture. Previous poem generation models only allow users to employ keywords to interfere the meaning of generated poems, leaving the dominion of generation to the model. In this paper, we propose a novel task of generating classical Chinese poems from vernacular, which allows users to have more control over the semantic of generated poems. We adapt the approach of unsupervised machine translation (UMT) to our task. We use segmentation-based padding and reinforcement learning to address under-translation and over-translation respectively. According to experiments, our approach significantly improve the perplexity and BLEU compared with typical UMT models. Furthermore, we explored guidelines on how to write the input vernacular to generate better poems. Human evaluation showed our approach can generate high-quality poems which are comparable to amateur poems.

We know that we used logo from Transformers in the featured image, so if you are a toy/movies/cartoon fan, sorry to disappoint you. We won't cover any of those topics in this blog post. However, if you are data science and deep learning fan, you are in the right place. In this article, we explore the interesting architecture of Transformers. They are a special type of sequence-to-sequence models used for language modeling, machine translation, image captioning and text generation.

Viewing scenes and making sense of them is something people do effortlessly every day. Whether it's sussing out objects' colors or gauging their distances apart, it doesn't take much conscious effort to recognize items' attributes and apply knowledge to answer questions about them. That's patently untrue of most AI systems, which tend to reason rather poorly. But emerging techniques in visual recognition, language understanding, and symbolic program execution promise to imbue them with the ability to generalize to new examples, much like humans. Scientists at the MIT-IBM Watson AI Lab, a joint 10-year, $240 million partnership to propel scientific breakthroughs in machine learning, are perfecting an approach they say might overcome longstanding barriers in AI model design.