The Artificial Intelligence Conference brings the growing AI community together to explore the most essential issues and intriguing innovations in applied AI. Are you a developer, engineer, designer, or product manager leveraging AI to build your company's next great product or service? Or an executive, entrepreneur, or innovator faced with making difficult strategic decisions to navigate the impact of AI on your organization? Join us at Artificial Intelligence and experience an unsurpassed depth and breadth in technical content--with a laser-sharp focus on the most important AI developments for business. Take a look at the schedule and start making your plans today.

GreyCampus is a leading provider of online self-learning courses for working professionals. This course is on Python, which is one of the easiest, most effective and most widely-used programming languages of today. Its efficient high-level data structures, simple yet effective approach to object-oriented programming, dynamic typing and elegant syntax, make Python an ideal language for both experts and novices for quick application development. The code is similar to English and doesn't need much technical knowledge to be read & understood. In this online self-learning course, you'll be taken through the very basics of Python assuming zero prior understanding of programming languages. This course mostly consists of hands-on examples for practical knowledge on Python and provides basic knowledge about the fundamentals of Python and its applications.

Want a robot that can navigate the world as easily as an animal? Then you have to design it to move the same way an animal does. This week, students enrolled in the University of Southern California's (USC's) Biologically Inspired Robotics course shared the results of their efforts to mimic animal movements in a robot. In a posted on the university's site, the students' mini robots – with characteristics reminiscent of cats, crabs, and other creatures – shuffle along adorably on their plastic and metal legs. Each bot completed a trek 30-times the length of its body -- the benchmark for success in the undergraduate course.

SAN JOSE, CA – Deep in central Mountain View, an hour's drive from the gleaming walls of Googleplex and the buzzing halls of innovation in San Jose, is a small building filled with busily whirring minds. This is not the corporate headquarters of another silicon start-up; this is the Menlo Park City School, and their kids are learning math. Menlo Park is an early adopter of the AltSchool model, a public partner in one of the most exciting new developments in the way we educate future generations since the late 19th century. For too long, children have stultified in a one-size-fits-all classroom model of learning: where a single teacher struggles to communicate a single set of information, at a set pace. But AltSchool is one of several new companies here to change that.

In the coming decade, this evolution will change the realities of work for everyone, which makes it a priority to gain further knowledge related to artificial intelligence. First and foremost, artificial intelligence is a support system that helps us focus on our strengths. As a university, we perceive our role as being an engine for this technological and societal revolution.»

A personalized learning system needs a large pool of items for learners to solve. When working with a large pool of items, it is useful to measure the similarity of items. We outline a general approach to measuring the similarity of items and discuss specific measures for items used in introductory programming. Evaluation of quality of similarity measures is difficult. To this end, we propose an evaluation approach utilizing three levels of abstraction. We illustrate our approach to measuring similarity and provide evaluation using items from three diverse programming environments.

In this paper, we introduce the Fairness GAN, an approach for generating a dataset that is plausibly similar to a given multimedia dataset, but is more fair with respect to protected attributes in allocative decision making. We propose a novel auxiliary classifier GAN that strives for demographic parity or equality of opportunity and show empirical results on several datasets, including the CelebFaces Attributes (CelebA) dataset, the Quick, Draw!\ dataset, and a dataset of soccer player images and the offenses they were called for. The proposed formulation is well-suited to absorbing unlabeled data; we leverage this to augment the soccer dataset with the much larger CelebA dataset. The methodology tends to improve demographic parity and equality of opportunity while generating plausible images.

Flood extent mapping plays a crucial role in addressing grand societal challenges such as disaster management, national water forecasting, as well as energy and food security. For example, during Hurricane Harvey floods in 2017, first responders needed to know where flood water was in order to plan rescue efforts. In national water forecasting, detailed flood extent maps can be used to calibrate and validate the NOAA National Water Model [15], which can forecast the flow of over 2.7 million rivers and streams through the entire continental U.S. [4]. In current practice, flood extent maps are mostly generated by flood forecasting models, whose accuracy is often unsatisfactory in high spatial details [4]. Other ways to generate flood maps involve sending field crew on the ground to record highwater marks, or visually interpreting earth observation imagery [2]. However, the process is both expensive and time consuming. With the large amount of high-resolution earth imagery being collected from satellites (e.g.,

Continual learning experiments used in current deep learning papers do not faithfully assess fundamental challenges of learning continually, masking weak-points of the suggested approaches instead. We study gaps in such existing evaluations, proposing essential experimental evaluations that are more representative of continual learning's challenges, and suggest a re-prioritization of research efforts in the field. We show that current approaches fail with our new evaluations and, to analyse these failures, we propose a variational loss which unifies many existing solutions to continual learning under a Bayesian framing, as either 'prior-focused' or 'likelihood-focused'. We show that while prior-focused approaches such as EWC and VCL perform well on existing evaluations, they perform dramatically worse when compared to likelihood-focused approaches on other simple tasks.

In recent years, sequence-to-sequence (seq2seq) models are used in a variety of tasks from machine translation, headline generation, text summarization, speech to text, to image caption generation. The underlying framework of all these models are usually a deep neural network which contains an encoder and decoder. The encoder processes the input data and a decoder receives the output of the encoder and generates the final output. Although simply using an encoder/decoder model would, most of the time, produce better result than traditional methods on the above-mentioned tasks, researchers proposed additional improvements over these sequence to sequence models, like using an attention-based model over the input, pointer-generation models, and self-attention models. However, all these seq2seq models suffer from two common problems: 1) exposure bias and 2) inconsistency between train/test measurement. Recently a completely fresh point of view emerged in solving these two problems in seq2seq models by using methods in Reinforcement Learning (RL). In these new researches, we try to look at the seq2seq problems from the RL point of view and we try to come up with a formulation that could combine the power of RL methods in decision-making and sequence to sequence models in remembering long memories. In this paper, we will summarize some of the most recent frameworks that combines concepts from RL world to the deep neural network area and explain how these two areas could benefit from each other in solving complex seq2seq tasks. In the end, we will provide insights on some of the problems of the current existing models and how we can improve them with better RL models. We also provide the source code for implementing most of the models that will be discussed in this paper on the complex task of abstractive text summarization.