Stanford graduate student Kaidi Cao will join fellow AI researchers Jing Liao, of City University of Hong Kong, and Lu Yuan of Microsoft at SIGGRAPH Asia in Tokyo this December to present their incredible caricature-drawing neural network. That's not bad, considering Cao was only an intern at the Visual Computing Group at the Microsoft Research Lab in Beijing when he worked on the project. The AI, actually a pair of generative adversarial networks (GAN), is called CariGANs. The first of its neural networks, CariGeoGAN, determines the geometry of a face in a photograph and maps it to a caricature model. CariStyGAN, the other half of CariGANs, does the "style transfer," or applies the artistic look to the geometry map.

It aims to provide students with an understanding of the role computation can play in solving problems and to help students, regardless of their major, feel justifiably confident of their ability to write small programs that allow them to accomplish useful goals. The class uses the Python 3.5 programming language.

Safe, controllable and credible artificial intelligence has been the goal which the humanity has been pursuing. In the field of machine learning, in order to achieve this goal, it is necessary for learning algorithm to really interact with the humanity; It is necessary for the learning algorithm to have the ability to correct errors, so as to avoid a prediction model with serious errors caused by unnecessary deviation in training data; It needs to be able to check its own learning process or decision-making process based on unsuccessful prediction results, especially for complex learning tasks; It is necessary to establish a learning algorithm for capturing and learning causal relationships in the world around us, so that the prediction model could predict what will happen under certain conditions, even if these conditions are significantly different from those of the past; It needs the learning algorithm which can really take full control of generalization performance of the prediction model. As big data accelerates transformation of scientific research pattern, scientific research is translating from a hypothetical drive mode to a data-driven one, which needs learning algorithm to discover new natural phenomena and laws through big data mining, statistic and analysis. However, recently, all of this is out of reach. The reason is that the prediction model and its training process are not yet understood by human beings, and are not covered by the knowledge base we currently have.

Deep neural networks are traditionally trained using human-designed stochastic optimization algorithms, such as SGD and Adam. Recently, the approach of learning to optimize network parameters has emerged as a promising research topic. However, these learned black-box optimizers sometimes do not fully utilize the experience in human-designed optimizers, therefore have limitation in generalization ability. In this paper, a new optimizer, dubbed as \textit{HyperAdam}, is proposed that combines the idea of "learning to optimize" and traditional Adam optimizer. Given a network for training, its parameter update in each iteration generated by HyperAdam is an adaptive combination of multiple updates generated by Adam with varying decay rates. The combination weights and decay rates in HyperAdam are adaptively learned depending on the task. HyperAdam is modeled as a recurrent neural network with AdamCell, WeightCell and StateCell. It is justified to be state-of-the-art for various network training, such as multilayer perceptron, CNN and LSTM.

An increasing number of datasets contain multiple views, such as video, sound and automatic captions. A basic challenge in representation learning is how to leverage multiple views to learn better representations. This is further complicated by the existence of a latent alignment between views, such as between speech and its transcription, and by the multitude of choices for the learning objective. We explore an advanced, correlation-based representation learning method on a 4-way parallel, multimodal dataset, and assess the quality of the learned representations on retrieval-based tasks. We show that the proposed approach produces rich representations that capture most of the information shared across views. Our best models for speech and textual modalities achieve retrieval rates from 70.7% to 96.9% on open-domain, user-generated instructional videos. This shows it is possible to learn reliable representations across disparate, unaligned and noisy modalities, and encourages using the proposed approach on larger datasets.

In discussions hosted on discussion forums for Massive Online Open Courses (MOOCs), references to online learning resources are often of central importance. However they are usually mentioned in free text, without appropriate hyperlinking to their associated resource. Automated learning resource mention hyperlinking and categorization will facilitate discussion and searching within MOOC forums, and also benefit the contextualization of such resources across disparate views. We propose the novel problem of learning resource mention identification inMOOC forums; i.e., to identify resource mentions in discussions, and classify them into predefined resource types. As this is a novel task with no publicly available data, we first contribute a large-scale labeled dataset - dubbed the Forum Resource Mention (FoRM) dataset - to facilitate our current research and future research on this task. FoRM contains over 10, 000 real-world forum threads in collaboration with Coursera, with more than 23, 000 manually labeled resource mentions. We then formulate this task as a sequence tagging problem and investigate solutionarchitectures to address the problem. Corresponding author Email address: peterpan10211020@gmail.com (Liangming Pan) Preprint submitted to Elsevier November 22, 2018 two major challenges that hinder the application of sequence tagging models tothe task: (1) the diversity of resource mention expression, and (2) long-range contextual dependencies. We address these challenges by incorporating character-leveland thread context information into a LSTM-CRF model. First, we incorporate a character encoder to address the out-ofvocabulary problemcaused by the diversity of mention expressions. Second, to address the context dependency challenge, we encode thread contexts using anRNN-based context encoder, and apply the attention mechanism to selectively leverage useful context information during sequence tagging. Experiments onFoRM show that the proposed method improves the baseline deep sequence tagging models notably, significantly bettering performance on instances that exemplify the two challenges.

On the 3:13 pm train out of San Jose on a recent Friday, I hunched over a Macbook, brow furrowed. Hundreds of miles north in a Google datacenter in Oregon, a virtual computer sprang to life. I was soon looking at the yawning blackness of a Linux command line--my new AI art studio. Some hours of Googling, mistyped commands, and muttered curses later, I was cranking out eerie portraits. I may reasonably be considered "good" with computers, but I'm no coder; I flunked out of Codecademy's easy-on-beginners online JavaScript course.

The fear of not having enough data can stall an enterprise's digital strategy. When you think you do not have much data, you stop to look at potential possibilities with existing data. However, it becomes a singular focus to collect additional data. You invest in making changes to your product to bring in sensors or vendors who coach you on how to collect additional data. Doing this without exploring what value you can bring in with existing data is equal to diversifying your portfolio without knowing your current asset allocation.

Location-based check-ins reveal a lot about a person -- and college students in particular, as it turns out. Researchers at Purdue University published a paper ("Exploring Student Check-In Behavior for Improved Point-of-Interest Prediction") on the preprint server Arxiv.org Predicting locations and friendships from location data with AI might sound a bit creepy, true. But on the plus side, it's not as dystopian as AI that can predict personality traits from eye movements. "In point-of-interest (POI) tasks, the goal is to use user behavioral data to model users' activities at different locations and times, and then make predictions (or recommendations for relevant venues based on their current context," the researchers wrote.

Professors and cognitive researchers frequently depend on test scores to determine how well students comprehend lessons. However, this practice ignores many critical aspects of learning, such as the engaging effect of classroom discussion or interests and motivations of classroom learners. By convention, a neutral observer would be required to recognize these unquantifiable moments of a great teaching experience but human observations are time-consuming and expensive. One can videotape classrooms, but that would be just as cumbersome and costly, requiring an expert to interpret and analyze the recordings afterwards. Because of advances in Artificial Intelligence, education researchers and computer scientists have come up with ways to create smart systems that can observe and listen in on classrooms, and instantaneously analyze the quality of a teacher's classroom delivery.