When people talk about artificial intelligence, they usually don't mean supervised and unsupervised machine learning. These tasks are pretty trivial compared to what we think of AIs doing - playing chess and Go, driving cars, and beating video games at a superhuman level. Reinforcement learning has recently become popular for doing all of that and more. Much like deep learning, a lot of the theory was discovered in the 70s and 80s but it hasn't been until recently that we've been able to observe first hand the amazing results that are possible. In 2016 we saw Google's AlphaGo beat the world Champion in Go.

Machine Learning and artificial intelligence (AI) is everywhere; if you want to know how companies like Google, Amazon, and even Udemy extract meaning and insights from massive data sets, this data science course will give you the fundamentals you need. Data Scientists enjoy one of the top-paying jobs, with an average salary of $120,000 according to Glassdoor and Indeed. If you've got some programming or scripting experience, this course will teach you the techniques used by real data scientists and machine learning practitioners in the tech industry - and prepare you for a move into this hot career path. This comprehensive machine learning tutorial includes over 100 lectures spanning 14 hours of video, and most topics include hands-on Python code examples you can use for reference and for practice. I'll draw on my 9 years of experience at Amazon and IMDb to guide you through what matters, and what doesn't.

Researchers are developing a deep learning network capable of detecting disease biomarkers with a much higher degree of accuracy. Experts at the University of Waterloo's Cheriton School of Computer Science have created a deep neural network that achieves 98 percent detection of peptide features in a dataset. That means scientists and medical practitioners have a greater chance of discovering possible diseases through tissue sample analysis. There are multiple existing techniques for detecting diseases by analyzing the protein structure of bio-samples. Computer programs increasingly play a part in this process by examining the large amount of data produced in such tests to pinpoint specific markers of disease.

In this paper, we investigate how to deploy computational intelligence and deep learning (DL) in edge-enabled industrial IoT networks. In this system, the IoT devices can collaboratively train a shared model without compromising data privacy. However, due to limited resources in the industrial IoT networks, including computational power, bandwidth, and channel state, it is challenging for many devices to accomplish local training and upload weights to the edge server in time. To address this issue, we propose a novel multi-exit-based federated edge learning (ME-FEEL) framework, where the deep model can be divided into several sub-models with different depths and output prediction from the exit in the corresponding sub-model. In this way, the devices with insufficient computational power can choose the earlier exits and avoid training the complete model, which can help reduce computational latency and enable devices to participate into aggregation as much as possible within a latency threshold. Moreover, we propose a greedy approach-based exit selection and bandwidth allocation algorithm to maximize the total number of exits in each communication round. Simulation experiments are conducted on the classical Fashion-MNIST dataset under a non-independent and identically distributed (non-IID) setting, and it shows that the proposed strategy outperforms the conventional FL. In particular, the proposed ME-FEEL can achieve an accuracy gain up to 32.7% in the industrial IoT networks with the severely limited resources.

Mental health is a critical issue in modern society, and mental disorders could sometimes turn to suicidal ideation without adequate treatment. Early detection of mental disorders and suicidal ideation from social content provides a potential way for effective social intervention. Recent advances in pretrained contextualized language representations have promoted the development of several domain-specific pretrained models and facilitated several downstream applications. However, there are no existing pretrained language models for mental healthcare. This paper trains and release two pretrained masked language models, i.e., MentalBERT and MentalRoBERTa, to benefit machine learning for the mental healthcare research community. Besides, we evaluate our trained domain-specific models and several variants of pretrained language models on several mental disorder detection benchmarks and demonstrate that language representations pretrained in the target domain improve the performance of mental health detection tasks.

Fast and accurate prediction of hurricane evolution from genesis onwards is needed to reduce loss of life and enhance community resilience. In this work, a novel model development methodology for predicting storm trajectory is proposed based on two classes of Recurrent Neural Networks (RNNs). The RNN models are trained on input features available in or derived from the HURDAT2 North Atlantic hurricane database maintained by the National Hurricane Center (NHC). The models use probabilities of storms passing through any location, computed from historical data. A detailed analysis of model forecasting error shows that Many-To-One prediction models are less accurate than Many-To-Many models owing to compounded error accumulation, with the exception of $6-hr$ predictions, for which the two types of model perform comparably. Application to 75 or more test storms in the North Atlantic basin showed that, for short-term forecasting up to 12 hours, the Many-to-Many RNN storm trajectory prediction models presented herein are significantly faster than ensemble models used by the NHC, while leading to errors of comparable magnitude.

Mathematical reasoning would be one of the next frontiers for artificial intelligence to make significant progress. The ongoing surge to solve math word problems (MWPs) and hence achieve better mathematical reasoning ability would continue to be a key line of research in the coming time. We inspect non-neural and neural methods to solve math word problems narrated in a natural language. We also highlight the ability of these methods to be generalizable, mathematically reasonable, interpretable, and explainable. Neural approaches dominate the current state of the art, and we survey them highlighting three strategies to MWP solving: (1) direct answer generation, (2) expression tree generation for inferring answers, and (3) template retrieval for answer computation. Moreover, we discuss technological approaches, review the evolution of intuitive design choices to solve MWPs, and examine them for mathematical reasoning ability. We finally identify several gaps that warrant the need for external knowledge and knowledge-infused learning, among several other opportunities in solving MWPs.

The Second Language Acquisition field has been significantly impacted by a greater emphasis on individualized learning and rapid developments in artificial intelligence (AI). Although increasingly adaptive language learning tools are being developed with the application of AI to the Computer Assisted Language Learning field, there have been concerns regarding insufficient information and teacher preparation. To effectively utilize these tools, teachers need an in-depth overview on recently developed AI-based language learning tools. Therefore, this review synthesized information on AI tools that were developed between 2017 and 2020. A majority of these tools utilized machine learning and natural language processing, and were used to identify errors, provide feedback, and assess language abilities. After using these tools, learners demonstrated gains in their language abilities and knowledge. This review concludes by presenting pedagogical implications and emerging themes in the future research of AI-based language learning tools.

Learned Iterative Shrinkage-Thresholding Algorithm (LISTA) introduces the concept of unrolling an iterative algorithm and training it like a neural network. It has had great success on sparse recovery. In this paper, we show that adding momentum to intermediate variables in the LISTA network achieves a better convergence rate and, in particular, the network with instance-optimal parameters is superlinearly convergent. Moreover, our new theoretical results lead to a practical approach of automatically and adaptively calculating the parameters of a LISTA network layer based on its previous layers. Perhaps most surprisingly, such an adaptive-parameter procedure reduces the training of LISTA to tuning only three hyperparameters from data: a new record set in the context of the recent advances on trimming down LISTA complexity. We call this new ultra-light weight network HyperLISTA. Compared to state-of-the-art LISTA models, HyperLISTA achieves almost the same performance on seen data distributions and performs better when tested on unseen distributions (specifically, those with different sparsity levels and nonzero magnitudes).

Despite strong performance in numerous applications, the fragility of deep learning to input perturbations has raised serious questions about its use in safety-critical domains. While adversarial training can mitigate this issue in practice, state-of-the-art methods are increasingly application-dependent, heuristic in nature, and suffer from fundamental trade-offs between nominal performance and robustness. Moreover, the problem of finding worst-case perturbations is non-convex and underparameterized, both of which engender a non-favorable optimization landscape. Thus, there is a gap between the theory and practice of adversarial training, particularly with respect to when and why adversarial training works. In this paper, we take a constrained learning approach to address these questions and to provide a theoretical foundation for robust learning. In particular, we leverage semi-infinite optimization and non-convex duality theory to show that adversarial training is equivalent to a statistical problem over perturbation distributions, which we characterize completely. Notably, we show that a myriad of previous robust training techniques can be recovered for particular, sub-optimal choices of these distributions. Using these insights, we then propose a hybrid Langevin Monte Carlo approach of which several common algorithms (e.g., PGD) are special cases. Finally, we show that our approach can mitigate the trade-off between nominal and robust performance, yielding state-of-the-art results on MNIST and CIFAR-10. Our code is available at: https://github.com/arobey1/advbench.