Recommending personalized learning materials for online language learning is challenging because we typically lack data about the student's ability and the relative difficulty of learning materials. This makes it hard to recommend appropriate content that matches the student's prior knowledge. In this paper, we propose a refined hierarchical knowledge structure to model vocabulary knowledge, which enables us to automatically organize the authentic and up-to-date learning materials collected from the internet. Based on this knowledge structure, we then introduce a hybrid approach to recommend learning materials that adapts to a student's language level. We evaluate our work with an online Japanese learning tool and the results suggest adding adaptivity into material recommendation significantly increases student engagement.

Graph neural networks have become one of the most important techniques to solve machine learning problems on graph-structured data. Recent work on vertex classification proposed deep and distributed learning models to achieve high performance and scalability. However, we find that the feature vectors of benchmark datasets are already quite informative for the classification task, and the graph structure only provides a means to denoise the data. In this paper, we develop a theoretical framework based on graph signal processing for analyzing graph neural networks. Our results indicate that graph neural networks only perform low-pass filtering on feature vectors and do not have the non-linear manifold learning property. We further investigate their resilience to feature noise and propose some insights on GCN-based graph neural network design.

In this work we address the problem of argument search. The purpose of argument search is the distillation of pro and contra arguments for requested topics from large text corpora. In previous works, the usual approach is to use a standard search engine to extract text parts which are relevant to the given topic and subsequently use an argument recognition algorithm to select arguments from them. The main challenge in the argument recognition task, which is also known as argument mining, is that often sentences containing arguments are structurally similar to purely informative sentences without any stance about the topic. In fact, they only differ semantically. Most approaches use topic or search term information only for the first search step and therefore assume that arguments can be classified independently of a topic. We argue that topic information is crucial for argument mining, since the topic defines the semantic context of an argument. Precisely, we propose different models for the classification of arguments, which take information about a topic of an argument into account. Moreover, to enrich the context of a topic and to let models understand the context of the potential argument better, we integrate information from different external sources such as Knowledge Graphs or pre-trained NLP models. Our evaluation shows that considering topic information, especially in connection with external information, provides a significant performance boost for the argument mining task.

In many real-world applications, one has to consider the minimization of several loss functions simultaneously, which is, of course, an impossible mission. Therefore, one objective is chosen as the primary function to minimize, leaving the others to be bound by predefined thresholds. For example, in online portfolio selection [5], the ultimate goal is to maximize the wealth of the investor while keeping the risk bounded by a user-defined constant. In the Neyman-Pearson (NP) classification (see, e.g., [22]), an extension of the classical binary classification, the goal is to learn a classifier achieving low type-II error whose type-I error is kept below a given threshold. Another example is the online job scheduling in distributed data centers (see, e.g., [14]), in which a job router receives job tasks and schedules them to different servers to fulfill the service. Each server purchases power (within its capacity) from its zone market, used for serving the assigned jobs. Electricity market prices can vary significantly across time and zones, and the goal is to minimize the electricity cost subject to the constraint that incoming jobs must be served in time. It is indeed possible to adjust any training algorithms capable of dealing with one objective loss to deal with multiple objectives by assigning a positive weight to each loss function. However, this modification turns out to be a difficult problem, especially in the case where one has to maintain the constraints below a given threshold online.

Symbol detection plays an important role in the implementation of digital receivers. In this work, we propose ViterbiNet, which is a data-driven symbol detector that does not require channel state information (CSI). ViterbiNet is obtained by integrating deep neural networks (DNNs) into the Viterbi algorithm. We identify the specific parts of the Viterbi algorithm that are channel-model-based, and design a DNN to implement only those computations, leaving the rest of the algorithm structure intact. We then propose a meta-learning based approach to train ViterbiNet online based on recent decisions, allowing the receiver to track dynamic channel conditions without requiring new training samples for every coherence block. Our numerical evaluations demonstrate that the performance of ViterbiNet, which is ignorant of the CSI, approaches that of the CSI-based Viterbi algorithm, and is capable of tracking time-varying channels without needing instantaneous CSI or additional training data. Moreover, unlike conventional Viterbi detection, ViterbiNet is robust to CSI uncertainty, and it can be reliably implemented in complex channel models with constrained computational burden. More broadly, our results demonstrate the conceptual benefit of designing communication systems to that integrate DNNs into established algorithms.

Machine learning promises methods that generalize well from finite labeled data. However, the brittleness of existing neural net approaches is revealed by notable failures, such as the existence of adversarial examples that are misclassified despite being nearly identical to a training example, or the inability of recurrent sequence-processing nets to stay on track without teacher forcing. We introduce a method, which we refer to as \emph{state reification}, that involves modeling the distribution of hidden states over the training data and then projecting hidden states observed during testing toward this distribution. Our intuition is that if the network can remain in a familiar manifold of hidden space, subsequent layers of the net should be well trained to respond appropriately. We show that this state-reification method helps neural nets to generalize better, especially when labeled data are sparse, and also helps overcome the challenge of achieving robust generalization with adversarial training.

An explosion in the growth of emerging technologies such as AI and machine learning is transforming the balance of skills required by modern analysts, research from business intelligence firm AMPLYFI has found. Using its own proprietary AI-powered DataVoyant platform, AMPLYFI has analysed more than 50,000 documents, held across the surface and deep web, to identify the most common skills and requirements associated with the job role'analyst' between 2009 and 2019. Research from SnapLogic finds inadequate access to AI skills, technology and data is holding AI initiatives back. An analyst's role has become elevated over time, delivering a much more integral business impact. The research found a marked rise in a need for business skills (up 76% in the last five years versus 2009-2014), problem-solving (112%), and verbal communications skills (19%).

What is machine learning, and what kinds of problems can it solve? What are the five phases of converting a candidate use case to be driven by machine learning, and why is it important that the phases not be skipped? Why are neural networks so popular now? How can you set up a supervised learning problem and find a good, generalizable solution using gradient descent and a thoughtful way of creating datasets? Learn how to write distributed machine learning models that scale in Tensorflow, scale out the training of those models.

Worried about the impact technology is having on your job? Stay curious and keep learning. That, in essence, is the message delivered by Google's country director for Canada, Sabrina Geremia, to participants on the last day of the C2 Montreal conference. "Disruption anxiety is in every single field," Geremia said Friday during an exchange with Jui Ramaprasad, a professor of information systems at McGill University. "Part of the anxiety is rooted in the pace of change. Right now, your life is the slowest it's ever going to be." Google's own statistics provide insights into the increasing speed of change.

By Rishi Mehra Artificial Intelligence (AI) and Machine Learning (ML) are the buzzwords in today's technology and business landscape. Both AI and ML are touted to give businesses the edge they need, improve efficiencies, make sales and marketing better and even help in critical HR functions. However, the general thought is that both these technologies are meant for larger companies and it makes little sense for smaller ones to embrace it. That may not be entirely true as technologies like AI & ML become ubiquitous. In fact, in some cases one may not even know the presence of such technologies in our everyday life.