Machine learning is an up and coming field with wider applications in various sectors including health, finance, retail, among others. If you are a beginner and want to pursue a career in emerging technologies like machine learning and deep learning, it's critical to have a first-hand experience of the concepts. Here is a curated list of 10 best machine learning projects that can help beginners kick start their ML journey. About: Sentiment analysis is an application in text mining and computational linguistics research to tease out the underlying sentiment in source texts. The in-depth analysis will help uncover market trends and consumer opinions, and offer insights for the overall improvement of products.

As part of our series showcasing the plenary and keynote talks from the IEEE/RSJ IROS2020 (International Conference on Intelligent Robots and Systems), this week we bring you Nikolaus Correll (Associate Professor at the University of Colorado at Boulder) and Cynthia Breazeal (Professor of Media Arts and Sciences at MIT). Nikolaus' talk is on the topic of robot manipulation, while Cynthia's talk is about the topic of social robots. Bio: Nikolaus Correll is an Associate Professor at the University of Colorado at Boulder. He obtained his MS in Electrical Engineering from ETH Zürich and his PhD in Computer Science from EPF Lausanne in 2007. From 2007-2009 he was a post-doc at MIT's Computer Science and Artificial Intelligence Lab (CSAIL).

Achievement tests for elementary and junior high school children across Japan showed no correlation between the percentages of correct answers and the lengths of coronavirus school closures, education ministry data showed Tuesday. Gaps in the average percentages of correct answers between the prefectures were also small. The tests for elementary school sixth-graders and junior high school third-graders were carried out in May after the cancellation last year due to blanket school closures triggered by the COVID-19 crisis. The tests measured achievement in Japanese language and arithmetic for elementary school students and in Japanese and mathematics for junior high school students. Some 1.97 million students at about 29,000 public and private schools participated, covering almost all public schools and about half of private schools in Japan.

Advances in technologies have continued to play an important role in healthcare, manufacturing, communication, travel, and also in education. The use of simulation technologies has proven to be a worthy element in the educational sector. The use of robotics in the education environment has exhibited an increased value in everyday learning. Machine learning and artificial intelligence are considered integral aspects of the future learning environment across the globe. Assimilating human learning attributes into the field of robotics can enable robots to distribute the integrated knowledge to students studying in colleges or universities.

With the increasing reliance on automated decision making, the issue of algorithmic fairness has gained increasing importance. In this paper, we propose a Generative Adversarial Network for tabular data generation. The model includes two phases of training. In the first phase, the model is trained to accurately generate synthetic data similar to the reference dataset. In the second phase we modify the value function to add fairness constraint, and continue training the network to generate data that is both accurate and fair. We test our results in both cases of unconstrained, and constrained fair data generation. In the unconstrained case, i.e. when the model is only trained in the first phase and is only meant to generate accurate data following the same joint probability distribution of the real data, the results show that the model beats state-of-the-art GANs proposed in the literature to produce synthetic tabular data. Also, in the constrained case in which the first phase of training is followed by the second phase, we train the network and test it on four datasets studied in the fairness literature and compare our results with another state-of-the-art pre-processing method, and present the promising results that it achieves. Comparing to other studies utilizing GANs for fair data generation, our model is comparably more stable by using only one critic, and also by avoiding major problems of original GAN model, such as mode-dropping and non-convergence, by implementing a Wasserstein GAN.

The powerful learning ability of deep neural networks enables reinforcement learning (RL) agents to learn competent control policies directly from high-dimensional and continuous environments. In theory, to achieve stable performance, neural networks assume i.i.d. inputs, which unfortunately does no hold in the general RL paradigm where the training data is temporally correlated and non-stationary. This issue may lead to the phenomenon of "catastrophic interference" and the collapse in performance as later training is likely to overwrite and interfer with previously learned policies. In this paper, we introduce the concept of "context" into single-task RL and develop a novel scheme, termed as Context Division and Knowledge Distillation (CDaKD) driven RL, to divide all states experienced during training into a series of contexts. Its motivation is to mitigate the challenge of aforementioned catastrophic interference in deep RL, thereby improving the stability and plasticity of RL models. At the heart of CDaKD is a value function, parameterized by a neural network feature extractor shared across all contexts, and a set of output heads, each specializing on an individual context. In CDaKD, we exploit online clustering to achieve context division, and interference is further alleviated by a knowledge distillation regularization term on the output layers for learned contexts. In addition, to effectively obtain the context division in high-dimensional state spaces (e.g., image inputs), we perform clustering in the lower-dimensional representation space of a randomly initialized convolutional encoder, which is fixed throughout training. Our results show that, with various replay memory capacities, CDaKD can consistently improve the performance of existing RL algorithms on classic OpenAI Gym tasks and the more complex high-dimensional Atari tasks, incurring only moderate computational overhead.

Modern product goals regardless of the domain rely a lot on algorithms solved by computers. Typical approaches adopt solutions based on heuristics, i.e., step-by-step instructions on how to finish tasks. Often times such approaches are not robust enough to tackle real-world situations. In presence of data representing those situations, Machine Learning (ML) is a very good approach that finds a probabilistic solution by learning from data.

The world's food system is in disarray. One in ten people is undernourished. One in four is overweight. More than one-third of the world's population cannot afford a healthy diet. Food supplies are disrupted by heatwaves, floods, droughts and wars.

With the rapid growth of research publications, empowering scientists to keep oversight over the scientific progress is of paramount importance. In this regard, the Leaderboards facet of information organization provides an overview on the state-of-the-art by aggregating empirical results from various studies addressing the same research challenge. Crowdsourcing efforts like PapersWithCode among others are devoted to the construction of Leaderboards predominantly for various subdomains in Artificial Intelligence. Leaderboards provide machine-readable scholarly knowledge that has proven to be directly useful for scientists to keep track of research progress. The construction of Leaderboards could be greatly expedited with automated text mining. This study presents a comprehensive approach for generating Leaderboards for knowledge-graph-based scholarly information organization. Specifically, we investigate the problem of automated Leaderboard construction using state-of-the-art transformer models, viz. Bert, SciBert, and XLNet. Our analysis reveals an optimal approach that significantly outperforms existing baselines for the task with evaluation scores above 90% in F1. This, in turn, offers new state-of-the-art results for Leaderboard extraction. As a result, a vast share of empirical AI research can be organized in the next-generation digital libraries as knowledge graphs.

Those designing autonomous systems that interact with humans will invariably face questions about how humans think and make decisions. Fortunately, computational cognitive science offers insight into human decision-making using tools that will be familiar to those with backgrounds in optimization and control (e.g., probability theory, statistical machine learning, and reinforcement learning). Here, we review some of this work, focusing on how cognitive science can provide forward models of human decision-making and inverse models of how humans think about others' decision-making. We highlight relevant recent developments, including approaches that synthesize blackbox and theory-driven modeling, accounts that recast heuristics and biases as forms of bounded optimality, and models that characterize human theory of mind and communication in decision-theoretic terms. In doing so, we aim to provide readers with a glimpse of the range of frameworks, methodologies, and actionable insights that lie at the intersection of cognitive science and control research.