Migrating a codebase from an archaic programming language such as COBOL to a modern alternative like Java or C is a difficult, resource-intensive task that requires expertise in both the source and target languages. COBOL, for example, is still widely used today in mainframe systems around the world, so companies, governments, and others often must choose whether to manually translate their code bases or commit to maintaining code written in a language that dates back to the 1950s. We've developed and open sourced TransCoder, an entirely self-supervised neural transcompiler system that can make code migration far easier and more efficient. Our method is the first AI system able to translate code from one programming language to another without requiring parallel data for training. We've demonstrated that TransCoder can successfully translate functions between C, Java, and Python 3. TransCoder outperforms open source and commercial rule-based translation programs.

In this work we propose the use of adaptive stochastic search as a building block for general, non-convex optimization operations within deep neural network architectures. Specifically, for an objective function located at some layer in the network and parameterized by some network parameters, we employ adaptive stochastic search to perform optimization over its output. This operation is differentiable and does not obstruct the passing of gradients during backpropagation, thus enabling us to incorporate it as a component in end-to-end learning. We study the proposed optimization module's properties and benchmark it against two existing alternatives on a synthetic energy-based structured prediction task, and further showcase its use in stochastic optimal control applications.

Carbon dioxide Capture and Storage (CCS) is an important strategy in mitigating anthropogenic CO$_2$ emissions. In order for CCS to be successful, large quantities of CO$_2$ must be stored and the storage site conformance must be monitored. Here we present a deep learning method to reconstruct pressure fields and classify the flux out of the storage formation based on the pressure data from Above Zone Monitoring Interval (AZMI) wells. The deep learning method is a version of a semi conditional variational auto-encoder tailored to solve two tasks: reconstruction of an incremental pressure field and leakage rate classification. The method, predictions and associated uncertainty estimates are illustrated on the synthetic data from a high-fidelity heterogeneous 2D numerical reservoir model, which was used to simulate subsurface CO$_2$ movement and pressure changes in the AZMI due to a CO$_2$ leakage.

Retrosynthesis is a problem to infer reactant compounds to synthesize a given product compound through chemical reactions. Recent studies on retrosynthesis focus on proposing more sophisticated prediction models, but the dataset to feed the models also plays an essential role in achieving the best generalizing models. Generally, a dataset that is best suited for a specific task tends to be small. In such a case, it is the standard solution to transfer knowledge from a large or clean dataset in the same domain. In this paper, we conduct a systematic and intensive examination of data transfer approaches on end-to-end generative models, in application to retrosynthesis. Experimental results show that typical data transfer methods can improve test prediction scores of an off-the-shelf Transformer baseline model. Especially, the pre-training plus fine-tuning approach boosts the accuracy scores of the baseline, achieving the new state-of-the-art. In addition, we conduct a manual inspection for the erroneous prediction results. The inspection shows that the pre-training plus fine-tuning models can generate chemically appropriate or sensible proposals in almost all cases.

Modern machine learning models (such as deep neural networks and boosting decision tree models) have become increasingly popular in financial market prediction, due to their superior capacity to extract complex non-linear patterns. However, since financial datasets have very low signal-to-noise ratio and are non-stationary, complex models are often very prone to overfitting and suffer from instability issues. Moreover, as various machine learning and data mining tools become more widely used in quantitative trading, many trading firms have been producing an increasing number of features (aka factors). Therefore, how to automatically select effective features becomes an imminent problem. To address these issues, we propose DoubleEnsemble, an ensemble framework leveraging learning trajectory based sample reweighting and shuffling based feature selection. Specifically, we identify the key samples based on the training dynamics on each sample and elicit key features based on the ablation impact of each feature via shuffling. Our model is applicable to a wide range of base models, capable of extracting complex patterns, while mitigating the overfitting and instability issues for financial market prediction. We conduct extensive experiments, including price prediction for cryptocurrencies and stock trading, using both DNN and gradient boosting decision tree as base models. Our experiment results demonstrate that DoubleEnsemble achieves a superior performance compared with several baseline methods.

The Large Scale Visual Recognition Challenge based on the well-known Imagenet dataset catalyzed an intense flurry of progress in computer vision. Benchmark tasks have propelled other sub-fields of machine learning forward at an equally impressive pace, but in healthcare it has primarily been image processing tasks, such as in dermatology and radiology, that have experienced similar benchmark-driven progress. In the present study, we performed a comprehensive review of benchmarks in medical machine learning for structured data, identifying one based on the Medical Information Mart for Intensive Care (MIMIC-III) that allows the first direct comparison of predictive performance and thus the evaluation of progress on four clinical prediction tasks: mortality, length of stay, phenotyping, and patient decompensation. We find that little meaningful progress has been made over a 3 year period on these tasks, despite significant community engagement. Through our meta-analysis, we find that the performance of deep recurrent models is only superior to logistic regression on certain tasks. We conclude with a synthesis of these results, possible explanations, and a list of desirable qualities for future benchmarks in medical machine learning.

Empirical studies suggest that wide neural networks are comparably easy to optimize, but mathematical support for this observation is scarce. In this paper, we analyze the optimization landscapes of deep learning with wide networks. We prove especially that constraint and unconstraint empirical-risk minimization over such networks has no spurious local minima. Hence, our theories substantiate the common belief that increasing network widths not only improves the expressiveness of deep-learning pipelines but also facilitates their optimizations. Deep learning depends on optimization problems that seem impossible to solve, and yet, deeplearning pipelines outperform their competitors in many applications. A common suspicion is that the optimizations are often easier than they appear to be. In particular, while most objective functions are nonconvex and, therefore, might have spurious local minima, recent findings suggest that optimizations are not hampered by spurious local minima as long as the neural networks are sufficiently wide.

Not all errors are created equal. This is especially true for many key machine learning applications. In the case of classification tasks, the severity of errors can be summarized under the form of a cost matrix, which assesses the gravity of confusing each pair of classes. When the target classes are organized into a hierarchical structure, this matrix defines a metric. We propose to integrate this metric in a new and versatile classification layer in order to model the disparity of errors. Our method relies on jointly learning a feature-extracting network and a set of class representations, or prototypes, which incorporate the error metric into their relative arrangement in the embedding space. Our approach allows for consistent improvement of the severity of the network's errors with regard to the cost matrix. Furthermore, when the induced metric contains insight on the data structure, our approach improves the overall precision as well. Experiments on four different public datasets -- from agricultural time series classification to depth image semantic segmentation -- validate our approach.

The field of machine translation (MT), the automatic translation of written text from one natural language into another, has experienced a major paradigm shift in recent years. Statistical MT, which mainly relies on various count-based models and which used to dominate MT research for decades, has largely been superseded by neural machine translation (NMT), which tackles translation with a single neural network. In this work we will trace back the origins of modern NMT architectures to word and sentence embeddings and earlier examples of the encoder-decoder network family. We will conclude with a short survey of more recent trends in the field.

Unsupervised clustering of temporal data is both challenging and crucial in machine learning. In this paper, we show that neither traditional clustering methods, time series specific or even deep learning-based alternatives generalise well when both varying sampling rates and high dimensionality are present in the input data. We propose a novel approach to temporal clustering, in which we (1) transform the input time series into a distance-based projected representation by using similarity measures suitable for dealing with temporal data,(2) feed these projections into a multi-layer CNN-GRU autoencoder to generate meaningful domain-aware latent representations, which ultimately (3) allow for a natural separation of clusters beneficial for most important traditional clustering algorithms. We evaluate our approach on time series datasets from various domains and show that it not only outperforms existing methods in all cases, by up to 32%, but is also robust and incurs negligible computation overheads.