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.

In real-world recognition/classification tasks, limited by various objective factors, it is usually difficult to collect training samples to exhaust all classes when training a recognizer or classifier. A more realistic scenario is open set recognition (OSR), where incomplete knowledge of the world exists at training time, and unknown classes can be submitted to an algorithm during testing, requiring the classifiers not only to accurately classify the seen classes, but also to effectively deal with the unseen ones. This paper provides a comprehensive survey of existing open set recognition techniques covering various aspects ranging from related definitions, representations of models, datasets, experiment setup and evaluation metrics. Furthermore, we briefly analyze the relationships between OSR and its related tasks including zero-shot, one-shot (few-shot) recognition/learning techniques, classification with reject option, and so forth. Additionally, we also overview the open world recognition which can be seen as a natural extension of OSR. Importantly, we highlight the limitations of existing approaches and point out some promising subsequent research directions in this field.

Attributed to its high learning capacity with good prediction capability, the deep neural network has found its advantage in wide areas of science and engineering applications. Such an observation has sparked a surge of investigations into the architectural and learning aspects of the deep network for targeted applications. The main ground for realizing the high learning capacity and predictivity comes from several major advancements in the field which include the processing platform, the learning regimen, and the availability of big data size. In terms of the processing platform, the advancement in Graphics Processing Units (GPUs) has facilitated parallel processing of complex network learning within accessible time. Together with the relatively low cost of the hardware, the large number of public high level open source libraries has enabled a crowdsourcing mode of learning architectural exploration. Based on such a learning platform, several learning regimens such as the Convolutional Neural Network (CNN or LeNet-5) [1], the AlexNet [2], the GoogLeNet or Inception [3], the Visual Geometry Group Network (VGG Net) [4], the Residual Network (ResNet) [5] and the DenseNet [6] have stretched the network learning in terms of the network depth and prediction capability way beyond the known boundary established by the conventional statistical methods. 2 Without sufficiently convincing explanation in theory, the advancement of deep learning has been grounded upon'big' data, powerful machinery and crowd efforts to achieve at'breakthrough' results that were not possible before. Such a swarming phenomenon has pushed forward the demand of hardware as well as middle ware, but at the expense of masking the importance of fundamental results available in statistical decision theory. The research scene has arrived at such a state of deeming results unacceptable without working directly on or comparing them with'big' data which implicitly relies on powerful machinery.

Noname manuscript No. (will be inserted by the editor) Abstract Learning classifier systems are evolutionary machine learning algorithms, flexible enough to be applied toreinforcement, supervised and unsupervised learning problems with good performance. Recently, self organizing classifierswere proposed which are similar to learning classifier systems but have the advantage that in its structured population no balance between niching and fitness pressure is necessary. However, more tests and analysis are required to verify its benefits. Here, a variation of the first algorithm is proposed which uses a parameterless self organizing map (SOM). This algorithm isapplied in challenging problems such as big, noisy as well as dynamically changing continuous inputaction mazes(growing and compressing mazes are included) withgood performance. Moreover, a genetic operator is proposed which utilizes the topological information ofthe SOM's population structure, improving the results. Thus, the first steps in structured evolutionary machinelearning are shown, nonetheless, the problems faced are more difficult than the state-of-art continuous input-action multi-step ones. 1 Introduction Learning Classifier Systems (LCS) are several algorithms inspired by evolution [29],[20]. Different from most reinforcement learning algorithms, however, LCS algorithms do not use state-action lookup tables to predict payoff. In this manner, the difficulties that arrive from complex problems, wherea large number of states and/or actions are required, can be avoided. Oneway of solving this problem is to separate a fitness defined on a niche from fitnesses defined on other niches (i.e., having a good fitness on other niches would not influence the present niche).