Over the past decade, designers have developed silicon technologies that run advanced deep learning mathematics fast enough to explore and implement artificial intelligence (AI) applications such as object identification, voice and facial recognition, and more. Machine vision applications, which are now often more accurate than a human, are one of the key functions driving new system-on-chip (SoC) investments to satisfy the development of AI for everyday applications. Using convolutional neural networks (CNNs) and other deep learning algorithms in vision applications have made such an impact that AI capabilities within SoCs are becoming pervasive. It was summarized effectively by Semico's 2018 AI Report "...some level of AI function in literally every type of silicon is strong and gaining momentum." In addition to vision, deep learning is used to solve complex problems such as 5G implementation for cellular infrastructure and simplifying 5G operational tasks through the capability to configure, optimize and repair itself, known as Self Organizing Networks (SON).

Machine learning gives us the ability to train a model, which can convert data rows into labels in such a way that similar data rows are mapped to similar or the same label. For example, we are building SPAM filter for email messages. We have a lot of email messages, some of which are marked as SPAM and some as INBOX. We can build a model, which learns to identify the SPAM messages. The messages to be marked as SPAM will be in some way similar to those, which are already marked as SPAM. The concept of similarity is vitally important for machine learning. In the real world, the concept of similarity is very specific to the subject matter and it depends on our knowledge.

At the International Conference on Learning Representations on May 6, IBM Research will share a deeper look around how chunk-based accumulation can speed the training for deep learning networks used for artificial intelligence (AI). The company first shared the concept and its vast potential at last year's NeurIPS conference, when it demonstrated the ability to train deep learning models with 8-bit precision while fully preserving model accuracy across all major AI data set categories: image, speech and text. This technique could accelerate training time for deep neural networks by two to four times over today's 16-bit systems. In IBM Research's new paper, titled "Accumulation Bit-Width Scaling For Ultralow Precision Training of Deep Networks," researchers explain in greater depth exactly how the concept of chunk-based accumulation works to lower the precision of accumulation from 32-bits down to 16-bits. "Chunking" takes the product and divides it into smaller groups of accumulation and then adds the result of each of these smaller groups together, leading to a significantly more accurate result than that of normal accumulation.

In my other posts, I have covered topics such as: How to combine machine learning and physics, and how machine learning can be used for production optimization as well as anomaly detection and condition monitoring. But in this post, I will discuss some of the common pitfalls of machine learning for time series forecasting. Time series forecasting is an important area of machine learning. It is important because there are so many prediction problems that involve a time component. However, while the time component adds additional information, it also makes time series problems more difficult to handle compared to many other prediction tasks.

Hackathons are an incredible medium for creating new ideas, new friends, and finding out about yourself. I don't code, at least not yet) I've always looked at hackathons with a sense of awe, as an unapproachable event that I always wanted to participate in. Well, I finally got my chance and it was an absolute blast! What was the hackathon all about?

Advances in computational science offer a principled pipeline for predictive modeling of cardiovascular flows and aspire to provide a valuable tool for monitoring, diagnostics and surgical planning. Such models can be nowadays deployed on large patient-specific topologies of systemic arterial networks and return detailed predictions on flow patterns, wall shear stresses, and pulse wave propagation. However, their success heavily relies on tedious pre-processing and calibration procedures that typically induce a significant computational cost, thus hampering their clinical applicability. In this work we put forth a machine learning framework that enables the seamless synthesis of non-invasive in-vivo measurement techniques and computational flow dynamics models derived from first physical principles. We illustrate this new paradigm by showing how one-dimensional models of pulsatile flow can be used to constrain the output of deep neural networks such that their predictions satisfy the conservation of mass and momentum principles. Once trained on noisy and scattered clinical data of flow and wall displacement, these networks can return physically consistent predictions for velocity, pressure and wall displacement pulse wave propagation, all without the need to employ conventional simulators. A simple post-processing of these outputs can also provide a cheap and effective way for estimating Windkessel model parameters that are required for the calibration of traditional computational models. The effectiveness of the proposed techniques is demonstrated through a series of prototype benchmarks, as well as a realistic clinical case involving in-vivo measurements near the aorta/carotid bifurcation of a healthy human subject.

There is a resurgent interest in developing intelligent open-domain dialog systems due to the availability of large amounts of conversational data and the recent progress on neural approaches to conversational AI. Unlike traditional task-oriented bots, an open-domain dialog system aims to establish long-term connections with users by satisfying the human need for communication, affection, and social belonging. This paper reviews the recent works on neural approaches that are devoted to addressing three challenges in developing such systems: semantics, consistency, and interactiveness. Semantics requires a dialog system to not only understand the content of the dialog but also identify user's social needs during the conversation. Consistency requires the system to demonstrate a consistent personality to win users trust and gain their long-term confidence. Interactiveness refers to the system's ability to generate interpersonal responses to achieve particular social goals such as entertainment, conforming, and task completion. The works we select to present here is based on our unique views and are by no means complete. Nevertheless, we hope that the discussion will inspire new research in developing more intelligent dialog systems.

Graph classification receives a great deal of attention from the non-Euclidean machine learning community. Recent advances in graph coarsening have enabled the training of deeper networks and produced new state-of-the-art results in many benchmark tasks. We examine how these architectures train and find that performance is highly-sensitive to initialisation and depends strongly on jumping-knowledge structures. We then show that, despite the great complexity of these models, competitive performance is achieved by the simplest of models -- structure-blind MLP, single-layer GCN and fixed-weight GCN -- and propose these be included as baselines in future.

There was a time when if anyone needed any news, he or she would wait for the next-day newspaper. However, with the growth of online newspapers who update news almost instantly, people have found a better and faster way to be informed of the matter of his/her interest. Nowadays social-networking systems, online news portals, and other online media have become the main sources of news through which interesting and breaking news are shared at a rapid pace. However, many news portals serve special interest by feeding with distorted, partially correct, and sometimes imaginary news that is likely to attract the attention of a target group of people. Fake news has become a major concern for being destructive sometimes spreading confusion and deliberate disinformation among the people.

The ability of neural networks to capture relational knowledge is a matter of long-standing controversy. Recently, some researchers in the PDP side of the debate have argued that (1) classic PDP models can handle relational structure (Rogers & McClelland, 2008, 2014) and (2) the success of deep learning approaches to text processing suggests that structured representations are unnecessary to capture the gist of human language (Rabovsky et al., 2018). In the present study we tested the Story Gestalt model (St. John, 1992), a classic PDP model of text comprehension, and a Sequence-to-Sequence with Attention model (Bahdanau et al., 2015), a contemporary deep learning architecture for text processing. Both models were trained to answer questions about stories based on the thematic roles that several concepts played on the stories. In three critical test we varied the statistical structure of new stories while keeping their relational structure constant with respect to the training data. Each model was susceptible to each statistical structure manipulation to a different degree, with their performance failing below chance at least under one manipulation. We argue that the failures of both models are due to the fact that they cannotperform dynamic binding of independent roles and fillers. Ultimately, these results cast doubts onthe suitability of traditional neural networks models for explaining phenomena based on relational reasoning, including language processing.