We propose a novel framework for non-parametric policy evaluation in static and dynamic settings. Under the assumption of selection on observables, we consider treatment effects of the population, of sub-populations, and of alternative populations that may have alternative covariate distributions. We further consider the decomposition of a total effect into a direct effect and an indirect effect (as mediated by a particular mechanism). Under the assumption of sequential selection on observables, we consider the effects of sequences of treatments. Across settings, we allow for treatments that may be discrete, continuous, or even text. Across settings, we allow for estimation of not only counterfactual mean outcomes but also counterfactual distributions of outcomes. We unify analyses across settings by showing that all of these causal learning problems reduce to the re-weighting of a prediction, i.e. causal adjustment. We implement the re-weighting as an inner product in a function space called a reproducing kernel Hilbert space (RKHS), with a closed form solution that can be computed in one line of code. We prove uniform consistency and provide finite sample rates of convergence. We evaluate our estimators in simulations devised by other authors. We use our new estimators to evaluate continuous and heterogeneous treatment effects of the US Jobs Corps training program for disadvantaged youth.

Learning under one-sided feedback (i.e., where we only observe the labels for examples we predicted positively on) is a fundamental problem in machine learning -- applications include lending and recommendation systems. Despite this, there has been surprisingly little progress made in ways to mitigate the effects of the sampling bias that arises. We focus on generalized linear models and show that without adjusting for this sampling bias, the model may converge suboptimally or even fail to converge to the optimal solution. We propose an adaptive approach that comes with theoretical guarantees and show that it outperforms several existing methods empirically. Our method leverages variance estimation techniques to efficiently learn under uncertainty, offering a more principled alternative compared to existing approaches.

Self-supervised learning and data augmentation have significantly reduced the performance gap between state and image-based reinforcement learning agents in continuous control tasks. However, it is still unclear whether current techniques can face a variety of visual conditions required by real-world environments. We propose a challenging benchmark that tests agents' visual generalization by adding graphical variety to existing continuous control domains. Our empirical analysis shows that current methods struggle to generalize across a diverse set of visual changes, and we examine the specific factors of variation that make these tasks difficult. We find that data augmentation techniques outperform self-supervised learning approaches and that more significant image transformations provide better visual generalization \footnote{The benchmark and our augmented actor-critic implementation are open-sourced @ https://github.com/jakegrigsby/dmc_remastered)

There is an increasing interest in the use of automatic mathematical word problem (MWP) generation in educational assessment. Different from standard natural question generation, MWP generation needs to maintain the underlying mathematical operations between quantities and variables, while at the same time ensuring the relevance between the output and the given topic. To address above problem we develop an end-to-end neural model to generate personalized and diverse MWPs in real-world scenarios from commonsense knowledge graph and equations. The proposed model (1) learns both representations from edgeenhanced Levi graphs of symbolic equations and commonsense knowledge; (2) automatically fuses equation and commonsense knowledge information via a selfplanning module when generating the MWPs. Experiments on an educational gold-standard set and a large-scale generated MWP set show that our approach is superior on the MWP generation task, and it outperforms the state-of-the-art models in terms of both automatic evaluation metrics, i.e., BLEU-4, ROUGE-L, Self-BLEU, and human evaluation metrics, i.e, equation relevance, topic relevance, and language coherence. A mathematical word problem (MWP) is a coherent narrative that provides clues to the underlying correct mathematical equations and operations between variables and numerical quantities (Verschaffel et al., 2000; Cetintas et al., 2010; Moyer et al., 1984). Table 1 shows one such problem where students are asked to infer the counts of chickens and rabbits. Mathematical Word Problem Equations Solutions Chickens and rabbits were in the yard. Together they had 27 heads x y 27 x 11 and 86 legs. How many chickens and rabbits were in the yard? In this paper, our objective is to automatically generate well-formed MWPs.

Within intelligent tutoring systems, considerable research has investigated hints, including how to generate data-driven hints, what hint content to present, and when to provide hints for optimal learning outcomes. However, less attention has been paid to how hints are presented. In this paper, we propose a new hint delivery mechanism called "Assertions" for providing unsolicited hints in a data-driven intelligent tutor. Assertions are partially-worked example steps designed to appear within a student workspace, and in the same format as student-derived steps, to show students a possible subgoal leading to the solution. We hypothesized that Assertions can help address the well-known hint avoidance problem. In systems that only provide hints upon request, hint avoidance results in students not receiving hints when they are needed. Our unsolicited Assertions do not seek to improve student help-seeking, but rather seek to ensure students receive the help they need. We contrast Assertions with Messages, text-based, unsolicited hints that appear after student inactivity. Our results show that Assertions significantly increase unsolicited hint usage compared to Messages. Further, they show a significant aptitude-treatment interaction between Assertions and prior proficiency, with Assertions leading students with low prior proficiency to generate shorter (more efficient) posttest solutions faster. We also present a clustering analysis that shows patterns of productive persistence among students with low prior knowledge when the tutor provides unsolicited help in the form of Assertions. Overall, this work provides encouraging evidence that hint presentation can significantly impact how students use them and using Assertions can be an effective way to address help avoidance.

NLU models often exploit biases to achieve high dataset-specific performance without properly learning the intended task. Recently proposed debiasing methods are shown to be effective in mitigating this tendency. However, these methods rely on a major assumption that the types of bias should be known a-priori, which limits their application to many NLU tasks and datasets. In this work, we present the first step to bridge this gap by introducing a self-debiasing framework that prevents models from mainly utilizing biases without knowing them in advance. The proposed framework is general and complementary to the existing debiasing methods. We show that it allows these existing methods to retain the improvement on the challenge datasets (i.e., sets of examples designed to expose models' reliance on biases) without specifically targeting certain biases. Furthermore, the evaluation suggests that applying the framework results in improved overall robustness.

Hands-on Training with "7 Stages of Machine Learning ... New What you'll learn Description " We will shift from a mobile first to an AI first world." AI will transform every industry similar to electricity over 100 years ago and have a huge impact on how humans live and work in the future. Moving into Data Science is an amazing career choice. There's high demand for Data Scientists across the globe and people working in the field enjoy high salaries and rewarding careers. For instance, average annual salaries are around $125,000 in America and ₹14 lacs in India.

Artificial Intelligence and Machine Learning are trending technologies today and an inherent part of the computer sciences that are also correlated. These are two hot buzzwords today. Essentially used for creating intelligent systems, we can say that AI is a bigger concept, involving the creation of intelligent machines, which have the capacity to simulate human thinking and behavior. On the other hand, machine learning is a subset of AI, allowing the machines, to learn from data without any sort of explicit programming. Today there are broad waves of technological change sweeping through the world and in it both these concepts have caught the imagination of the people. This is an exercise to understand both the terms so that the basic differences are understood through this understanding and analysis.

The Indian Institute of Technology Jodhpur is launching a new BTech programme in artificial intelligence and data science from the academic session 2020-21. The new undergraduate programme will have courses in computer science, mathematics, artificial intelligence, machine learning, data science, and their applications in various domains. According to the institute, students, once opted for the course, will be able to take a specialisation in various areas including visual computing, socio-digital realities, language technologies, robotics, and artificial intelligence and others. In IIT-Jodhpur's official release, it has been mentioned that, with the course, enrolling students will also have the option to take up MBA (tech) in their fifth year as a dual-degree option in the School of Management and Entrepreneurship. Prof Santanu Chaudhury, Director, IIT-Jodhpur, said that, with the vision of creating AI for everything, "students belonging to the academic programmes in artificial intelligence, data and computational sciences will be part of scientific innovations for addressing local and global engineering and social problems in close collaboration with industry."

We're in 2020 and long past the days back when we used to stand outside the school library to get the opportunity to copy two or three Encyclopedia pages, to use as a kind of reference for our school projects. With this age having grown up with the benefit of access to technology at their fingertips, the field of education has hugely changed and overturned in this digitally driven world. Artificial Intelligence in the education market was worth US$2.022 billion for the year 2019. The worldwide AI in the education market is anticipated to be valued at USD 3.68 billion by 2023, at a CAGR of 47% during the forecast period of 2018 till 2023. Artificial intelligence has already infiltrated our lives on an individual level.