We present ASDiv (Academia Sinica Diverse MWP Dataset), a diverse (in terms of both language patterns and problem types) English math word problem (MWP) corpus for evaluating the capability of various MWP solvers. Existing MWP corpora for studying AI progress remain limited either in language usage patterns or in problem types. We thus present a new English MWP corpus with 2,305 MWPs that cover more text patterns and most problem types taught in elementary school. Each MWP is annotated with its problem type and grade level (for indicating the level of difficulty). Furthermore, we propose a metric to measure the lexicon usage diversity of a given MWP corpus, and demonstrate that ASDiv is more diverse than existing corpora. Experiments show that our proposed corpus reflects the true capability of MWP solvers more faithfully.

This paper surveys the field of multiagent deep reinforcement learning. The combination of deep neural networks with reinforcement learning has gained increased traction in recent years and is slowly shifting the focus from single-agent to multiagent environments. Dealing with multiple agents is inherently more complex as (a) the future rewards depend on the joint actions of multiple players and (b) the computational complexity of functions increases. We present the most common multiagent problem representations and their main challenges, and identify five research areas that address one or more of these challenges: centralised training and decentralised execution, opponent modelling, communication, efficient coordination, and reward shaping. We find that many computational studies rely on unrealistic assumptions or are not generalisable to other settings; they struggle to overcome the curse of dimensionality or nonstationarity. Approaches from psychology and sociology capture promising relevant behaviours such as communication and coordination. We suggest that, for multiagent reinforcement learning to be successful, future research addresses these challenges with an interdisciplinary approach to open up new possibilities for more human-oriented solutions in multiagent reinforcement learning.

Deep learning based image recognition systems have been widely deployed on mobile devices in today's world. In recent studies, however, deep learning models are shown vulnerable to adversarial examples. One variant of adversarial examples, called adversarial patch, draws researchers' attention due to its strong attack abilities. Though adversarial patches achieve high attack success rates, they are easily being detected because of the visual inconsistency between the patches and the original images. Besides, it usually requires a large amount of data for adversarial patch generation in the literature, which is computationally expensive and time-consuming. To tackle these challenges, we propose an approach to generate inconspicuous adversarial patches with one single image. In our approach, we first decide the patch locations basing on the perceptual sensitivity of victim models, then produce adversarial patches in a coarse-to-fine way by utilizing multiple-scale generators and discriminators. The patches are encouraged to be consistent with the background images with adversarial training while preserving strong attack abilities. Our approach shows the strong attack abilities in white-box settings and the excellent transferability in black-box settings through extensive experiments on various models with different architectures and training methods. Compared to other adversarial patches, our adversarial patches hold the most negligible risks to be detected and can evade human observations, which is supported by the illustrations of saliency maps and results of user evaluations. Lastly, we show that our adversarial patches can be applied in the physical world.

Taught by Professor Mausam of the Indian Institute of Technology, Delhi, it discusses the philosophy of AI and how to model a new problem as an AI problem. It describes a variety of basic components of AI, such as search and logic, which can be used to model and solve a new problem. It also teaches many primary algorithms (a process or set of rules) to solve each formulation. The course prepares a student to take a variety of advanced courses in various subfields of AI. This teaches you the meaning of common AI terminology.

We know that digital and AI technologies are transforming the world of work and that today's workforce will need to learn new skills and learn to continually adapt as new occupations emerge. We also know that the COVID-19 crisis has accelerated this transformation. We are less clear, however, about the specific skills tomorrow's workers will require. Research by the McKinsey Global Institute has looked at the kind of jobs that will be lost, as well as those that will be created, as automation, AI, and robotics take hold. And it has inferred the type of high-level skills that will become increasingly important as a result. 1 1.

Educational programs, whether that may be an online course, an article even, or an undergraduate and graduate program, often neglect the professional aspect of data science. Of course, highly complex, machine learning algorithms and deployment of models is incredibly important to learn, but there are some other aspects of data science that are especially important as a professional data scientist or data scientist that is more customer-facing. A customer also does not necessarily mean the customer of a product, but the customer of your company, as in the stakeholder. With that being said, let's discuss three critical soft skills that every data scientist should know as they transition from a student of data science in education to a professional data scientist. This point is both a skill and a reminder that you do not work alone as a data scientist.

In this series, we are going to write a neural net completely from scratch (down to rudimentary tensor operations) with Nvidia's CUDA, the GPU parallel computing platform behind modern deep learning libraries. You can find the GitHub repository here. Audience: Familiarity with core concepts of C, such as pointers and object-oriented programming, is needed, and you must be thoroughly comfortable with neural networks and their various aspects like backpropagation. However, you need not know any CUDA or parallel programming, and everything will be covered in the upcoming articles. Without further ado, let's get coding!

Education sector is integrating personalized learning process with the implementation of AI in learning apps. Artificial Intelligence for education purposes is both beneficial to the teachers and children after adopting AI systems in digital education.

An important challenge in reinforcement learning is training agents that can solve a wide variety of tasks. If tasks depend on each other (e.g. needing to learn to walk before learning to run), curriculum learning can speed up learning by focusing on the next best task to learn. We explore curriculum learning in a complex, visual domain with many hard exploration challenges: Minecraft. We find that learning progress (defined as a change in success probability of a task) is a reliable measure of learnability for automatically constructing an effective curriculum. We introduce a learning-progress based curriculum and test it on a complex reinforcement learning problem (called "Simon Says") where an agent is instructed to obtain a desired goal item. Many of the required skills depend on each other. Experiments demonstrate that: (1) a within-episode exploration bonus for obtaining new items improves performance, (2) dynamically adjusting this bonus across training such that it only applies to items the agent cannot reliably obtain yet further increases performance, (3) the learning-progress based curriculum elegantly follows the learning curve of the agent, and (4) when the learning-progress based curriculum is combined with the dynamic exploration bonus it learns much more efficiently and obtains far higher performance than uniform baselines. These results suggest that combining intra-episode and across-training exploration bonuses with learning progress creates a promising method for automated curriculum generation, which may substantially increase our ability to train more capable, generally intelligent agents.

Motivated by emerging applications such as live-streaming e-commerce, promotions and recommendations, we introduce a general class of multi-armed bandit problems that have the following two features: (i) the decision maker can pull and collect rewards from at most $K$ out of $N$ different arms in each time period; (ii) the expected reward of an arm immediately drops after it is pulled, and then non parametrically recovers as the idle time increases. With the objective of maximizing expected cumulative rewards over $T$ time periods, we propose, construct and prove performance guarantees for a class of "Purely Periodic Policies". For the offline problem when all model parameters are known, our proposed policy obtains an approximation ratio that is at the order of $1-\mathcal O(1/\sqrt{K})$, which is asymptotically optimal when $K$ grows to infinity. For the online problem when the model parameters are unknown and need to be learned, we design an Upper Confidence Bound (UCB) based policy that approximately has $\widetilde{\mathcal O}(N\sqrt{T})$ regret against the offline benchmark. Our framework and policy design may have the potential to be adapted into other offline planning and online learning applications with non-stationary and recovering rewards.