Neural transducer is now the most popular end-to-end model for speech recognition, due to its naturally streaming ability. However, it is challenging to adapt it with text-only data. Factorized neural transducer (FNT) model was proposed to mitigate this problem. The improved adaptation ability of FNT on text-only adaptation data came at the cost of lowered accuracy compared to the standard neural transducer model. We propose several methods to improve the performance of the FNT model. They are: adding CTC criterion during training, adding KL divergence loss during adaptation, using a pre-trained language model to seed the vocabulary predictor, and an efficient adaptation approach by interpolating the vocabulary predictor with the n-gram language model. A combination of these approaches results in a relative word-error-rate reduction of 9.48\% from the standard FNT model. Furthermore, n-gram interpolation with the vocabulary predictor improves the adaptation speed hugely with satisfactory adaptation performance.

Cutting plane selection is a subroutine used in all modern mixed-integer linear programming solvers with the goal of selecting a subset of generated cuts that induce optimal solver performance. These solvers have millions of parameter combinations, and so are excellent candidates for parameter tuning. Cut selection scoring rules are usually weighted sums of different measurements, where the weights are parameters. We present a parametric family of mixed-integer linear programs together with infinitely many family-wide valid cuts. Some of these cuts can induce integer optimal solutions directly after being applied, while others fail to do so even if an infinite amount are applied. We show for a specific cut selection rule, that any finite grid search of the parameter space will always miss all parameter values, which select integer optimal inducing cuts in an infinite amount of our problems. We propose a variation on the design of existing graph convolutional neural networks, adapting them to learn cut selection rule parameters. We present a reinforcement learning framework for selecting cuts, and train our design using said framework over MIPLIB 2017 and a neural network verification data set. Our framework and design show that adaptive cut selection does substantially improve performance over a diverse set of instances, but that finding a single function describing such a rule is difficult. Code for reproducing all experiments is available at https://github.com/Opt-Mucca/Adaptive-Cutsel-MILP.

This paper presents work on novel machine translation (MT) systems between spoken and signed languages, where signed languages are represented in SignWriting, a sign language writing system. Our work seeks to address the lack of out-of-the-box support for signed languages in current MT systems and is based on the SignBank dataset, which contains pairs of spoken language text and SignWriting content. We introduce novel methods to parse, factorize, decode, and evaluate SignWriting, leveraging ideas from neural factored MT. In a bilingual setup--translating from American Sign Language to (American) English--our method achieves over 30 BLEU, while in two multilingual setups--translating in both directions between spoken languages and signed languages--we achieve over 20 BLEU. We find that common MT techniques used to improve spoken language translation similarly affect the performance of sign language translation. These findings validate our use of an intermediate text representation for signed languages to include them in natural language processing research.

Online optimization is a well-established optimization paradigm that aims to make a sequence of correct decisions given knowledge of the correct answer to previous decision tasks. Bilevel programming involves a hierarchical optimization problem where the feasible region of the so-called outer problem is restricted by the graph of the solution set mapping of the inner problem. This paper brings these two ideas together and studies an online bilevel optimization setting in which a sequence of time-varying bilevel problems are revealed one after the other. We extend the known regret bounds for single-level online algorithms to the bilevel setting. Specifically, we introduce new notions of bilevel regret, develop an online alternating time-averaged gradient method that is capable of leveraging smoothness, and provide regret bounds in terms of the path-length of the inner and outer minimizer sequences.

A logged forest in the Amazon. A collaboration led by Ekena Rangel Pinagé (Oregon State University) has used very-high-resolution satellite imagery to develop a machine learning model that aims to improve climate scientists' ability to estimate aboveground carbon stocks in the Amazon. Findings of the study were published in the journal Carbon Balance and Management. Covering more than 2.5 million square miles in South America, the Amazon is the largest of the world's tropical forests, which play huge ecological roles for the planet despite covering less than 10% of the Earth's land area. More than half of all carbon stored in aboveground biomass is sequestered in tropical rain forests, which are also home to greater than 60% of all terrestrial species.

AI in pharma refers to the use of automated algorithms to jobs that normally need human intelligence. Large datasets including disease patterns can be successfully identified by AI solutions in pharma, and they can also assist in understanding which medication formulations would be most effective for treating certain ailments. The artificial intelligence (AI) in the pharma market covered in the report is segmented by technology into context-aware processing, natural language processing, querying method, and deep learning; by drug type into the small molecule, large molecules; by application into diagnosis, clinical trial research, drug discovery, research and development, epidemic prediction. The artificial intelligence (AI) in pharma market research report is one of a series of new reports from The Business Research Company that provides artificial intelligence (AI) in pharma market statistics, including artificial intelligence (AI) in pharma industry global market size, regional shares, competitors with artificial intelligence (AI) in pharma market share, detailed artificial intelligence (AI) in pharma market segments, market trends and opportunities, and any further data you may need to thrive in the artificial intelligence (AI) in pharma industry. This artificial intelligence (AI) in pharma market research report delivers a complete perspective of everything you need, with an in-depth analysis of the current and future scenario of the industry.

To date, much of the algorithmic fairness literature has focused on the fairness of classification systems which are used, for example, to decide whether a person should be granted a loan or be released from prison on bail. Even in cases where such classification decisions are based on risk score models - such as in the highly influential COMPAS case [5, 11, 16] - their fairness is typically considered a function of the decisions, or classifications, made by the system. Of course, any risk score model can be turned into a classifier by selecting a probability threshold (in binary classification) or predicting the most likely outcome (in multi-class classification). Nevertheless, we argue here that it is worthwhile to distinguish between these two settings and consider the fairness of risk models independent of their downstream use, be it as the basis for a classifier or otherwise. We discuss notions of fairness for risk scores as well as their relationship to classical, classification-level notions of fairness, and we develop robust tools to empirically quantify risk score fairness. We illustrate our methodology in two case studies, one situated in the criminal justice system and one in healthcare. Why distinguish between fair models and fair decisions? In the statistical literature, it is generally considered desirable to distinguish between inference (e.g., identifying a risk score model) and subsequent decision-making (e.g., deriving a classification from a risk score model): while the former represents a purely statistical task, the latter depends on subjective

Transfer learning has recently become the dominant paradigm of machine learning. Pre-trained models fine-tuned for downstream tasks achieve better performance with fewer labelled examples. Nonetheless, it remains unclear how to develop models that specialise towards multiple tasks without incurring negative interference and that generalise systematically to non-identically distributed tasks. Modular deep learning has emerged as a promising solution to these challenges. In this framework, units of computation are often implemented as autonomous parameter-efficient modules. Information is conditionally routed to a subset of modules and subsequently aggregated. These properties enable positive transfer and systematic generalisation by separating computation from routing and updating modules locally. We offer a survey of modular architectures, providing a unified view over several threads of research that evolved independently in the scientific literature. Moreover, we explore various additional purposes of modularity, including scaling language models, causal inference, programme induction, and planning in reinforcement learning. Finally, we report various concrete applications where modularity has been successfully deployed such as cross-lingual and cross-modal knowledge transfer. Related talks and projects to this survey, are available at https://www.modulardeeplearning.com/.

In semi-supervised learning, student-teacher distribution matching has been successful in improving performance of models using unlabeled data in conjunction with few labeled samples. In this paper, we aim to replicate that success in the self-supervised setup where we do not have access to any labeled data during pre-training. We introduce our algorithm, Q-Match, and show it is possible to induce the student-teacher distributions without any knowledge of downstream classes by using a queue of embeddings of samples from the unlabeled dataset. We focus our study on tabular datasets and show that Q-Match outperforms previous self-supervised learning techniques when measuring downstream classification performance. Furthermore, we show that our method is sample efficient-in terms of both the labels required for downstream training and the amount of unlabeled data required for pre-training-and scales well to the sizes of both the labeled and unlabeled data. Tabular data is the most common form of data for problems in industry. While many robust techniques exist to solve real-world machine learning problems on tabular data, most of these techniques require access to labels. Leveraging unlabeled data to learn good representations remains a key open problem in the tabular domain. In this work, we propose a flexible and powerful framework using deep learning that helps us use unlabeled data in the tabular domain. Deep learning has been successful in processing data in many different domains like images, audio, and text.

To design with AI models, user experience (UX) designers must assess the fit between the model and user needs. Based on user research, they need to contextualize the model's behavior and potential failures within their product-specific data instances and user scenarios. However, our formative interviews with ten UX professionals revealed that such a proactive discovery of model limitations is challenging and time-intensive. Furthermore, designers often lack technical knowledge of AI and accessible exploration tools, which challenges their understanding of model capabilities and limitations. In this work, we introduced a failure-driven design approach to AI, a workflow that encourages designers to explore model behavior and failure patterns early in the design process. The implementation of fAIlureNotes, a designer-centered failure exploration and analysis tool, supports designers in evaluating models and identifying failures across diverse user groups and scenarios. Our evaluation with UX practitioners shows that fAIlureNotes outperforms today's interactive model cards in assessing context-specific model performance.