My Husky Experience has enabled me to break the glass ceiling instead of fitting into a glass slipper. Over the years, my experiences with being a leader in the UW Society of Women Engineers (SWE), the Foundation for International Understanding Through Students (FIUTS), Residence Education Programmers (REP), working as a teaching assistant for iSchool classes, researching Women Affinity Groups in the tech industry and social robots in high schools have helped me grow from a naive freshman into a confident data scientist, teacher and researcher with a passion to use my experiences to serve society by uplifting those around me.

Neural networks are effective function approximators, but hard to train in the reinforcement learning (RL) context mainly because samples are correlated. For years, scholars have got around this by employing experience replay or an asynchronous parallel-agent system. This paper proposes Discrete-to-Deep Supervised Policy Learning (D2D-SPL) for training neural networks in RL. D2D-SPL discretises the continuous state space into discrete states and uses actor-critic to learn a policy. It then selects from each discrete state an input value and the action with the highest numerical preference as an input/target pair. Finally it uses input/target pairs from all discrete states to train a classifier. D2D-SPL uses a single agent, needs no experience replay and learns much faster than state-of-the-art methods. We test our method with two RL environments, the Cartpole and an aircraft manoeuvring simulator.

We present Korbit, a large-scale, open-domain, mixed-interface, dialogue-based intelligent tutoring system (ITS). Korbit uses machine learning, natural language processing and reinforcement learning to provide interactive, personalized learning online. Korbit has been designed to easily scale to thousands of subjects, by automating, standardizing and simplifying the content creation process. Unlike other ITS, a teacher can develop new learning modules for Korbit in a matter of hours. To facilitate learning across a widerange of STEM subjects, Korbit uses a mixed-interface, which includes videos, interactive dialogue-based exercises, question-answering, conceptual diagrams, mathematical exercises and gamification elements. Korbit has been built to scale to millions of students, by utilizing a state-of-the-art cloud-based micro-service architecture. Korbit launched its first course in 2019 on machine learning, and since then over 7,000 students have enrolled. Although Korbit was designed to be open-domain and highly scalable, A/B testing experiments with real-world students demonstrate that both student learning outcomes and student motivation are substantially improved compared to typical online courses.

We introduce learning programs by learning from failures. In this approach, an inductive logic programming (ILP) system (the learner) decomposes the learning problem into three separate stages: generate, test, and constrain. In the generate stage, the learner generates a hypothesis (a logic program) that satisfies a set of hypothesis constraints (constraints on the syntactic form of hypotheses). In the test stage, the learner tests the hypothesis against training examples. A hypothesis fails when it does not entail all the positive examples or entails a negative example. If a hypothesis fails, then, in the constrain stage, the learner learns constraints from the failed hypothesis to prune the hypothesis space, i.e. to constrain subsequent hypothesis generation. For instance, if a hypothesis is too general (entails a negative example), the constraints prune generalisations of the hypothesis. If a hypothesis is too specific (does not entail all the positive examples), the constraints prune specialisations of the hypothesis. This loop repeats until (1) the learner finds a hypothesis that entails all the positive and none of the negative examples, or (2) there are no more hypotheses to test. We implement our idea in Popper, an ILP system which combines answer set programming and Prolog. Popper supports infinite domains, reasoning about lists and numbers, learning optimal (textually minimal) programs, and learning recursive programs. Our experimental results on three diverse domains (number theory problems, robot strategies, and list transformations) show that (1) constraints drastically improve learning performance, and (2) Popper can substantially outperform state-of-the-art ILP systems, both in terms of predictive accuracies and learning times.

We propose a simple yet powerful test statistic to quantify the discrepancy between two conditional distributions. The new statistic avoids the explicit estimation of the underlying distributions in highdimensional space and it operates on the cone of symmetric positive semidefinite (SPS) matrix using the Bregman matrix divergence. Moreover, it inherits the merits of the correntropy function to explicitly incorporate high-order statistics in the data. We present the properties of our new statistic and illustrate its connections to prior art. We finally show the applications of our new statistic on three different machine learning problems, namely the multi-task learning over graphs, the concept drift detection, and the information-theoretic feature selection, to demonstrate its utility and advantage. Code of our statistic is available at https://bit.ly/BregmanCorrentropy.

The College of Engineering Awards acknowledge the extraordinary efforts of the college's teaching and research assistants, staff, and faculty members. The College of Engineering Awards ceremony scheduled for April 20 has been canceled. Since joining UW in 2014, Cole DeForest has established himself as an innovative researcher, an effective teacher and a collaborative colleague, holding appointments in Chemical Engineering, Bioengineering, and the Institute for Stem Cell & Regenerative Medicine. His research focuses on the development of (de)polymerization reactions that can be triggered using light in the presence of cells, and "represents a major advancement in cell culture niches that allow unprecedented control of the cellular microenvironment, and is enabling him to conduct newfound experiments that were previously impossible." Cole has received numerous honors, including an NSF Career Award, a Young Investigator Award through the American Chemical Society, and a UW Presidential Distinguished Teaching Award.

The market for online courses is growing sharply. It will be worth $243 billion by 2022. One of the reasons online courses are becoming more popular is that big data has made them more effective. Big data has created countless changes in recent years. It has played a very important role in the development of online courses.

The propagation of Artificial Intelligence (AI) as new technology has received worldwide recognition. Although it's not a new concept, the implementation of AI techniques across software testing has proven advantageous. It is interesting to know that, development teams across various platforms are switching to online and e-learning assets all thanks to AI. However, the misery for QA Engineers at present is linked to surplus difficulties and time wastage while looking for a solution. The scope for making new additions or expanding existing new codes requires them to carry out fresh tests.

Using a new method that employs artificial intelligence, a teacher can teach the computer by demonstrating several ways to solve problems in a topic, such as multicolumn addition, and correcting the computer if it responds incorrectly. Notably, the computer system learns to not only solve the problems in the ways it was taught, but also to generalize to solve all other problems in the topic, and do so in ways that might differ from those of the teacher, said Daniel Weitekamp III, a Ph.D. student in CMU's Human-Computer Interaction Institute (HCII). "A student might learn one way to do a problem and that would be sufficient," Weitekamp explained. "But a tutoring system needs to learn every kind of way to solve a problem." It needs to learn how to teach problem solving, not just how to solve problems.

Instructor very knowledgeable about the material, and explains it clearly and to the point. Also, gives very good practical examples. As usual, Mike provides a well made course to teach you about SciKit. The lessons are very short so you are able to absorb the information, and the follow up labs help anchor what you learned. I will be going over this course again because the information is a bit advanced, but I already got a great understanding and feel for SciKit after my first go through of the course.