The first three entries in my "2020: A consumer electronics forecast for the year(s) ahead" piece, published back in January, all had to do with deep learning. Why? Here's part of what I wrote back then: The ability to pattern-match and extrapolate from already-identified data ("training") to not-yet-identified data ("inference") has transformed the means by which many algorithms are developed nowadays, with impact on numerous applications. This transformation is already well underway, as even a casual perusal of the titles and coverage topics of content published at EDN, EE Times, and elsewhere will make clear. Don't panic: there's still time to "catch the wave," especially if your focus is on resource-constrained implementations. But you don't want to wait too long lest you end up stuck bobbing around in the water while more foresighted colleagues are already at the beach enjoying the AI "party."

You see that the politician in question is saying something outrageous. The sheer ridiculousness of his speech makes you forward it in your own circle, only to realise much later that the video was manipulated. But by now, the video has been circulated wide and far, with almost no way to recall it back. Such hyper-realistic manipulated videos are called deepfakes. These videos leverage powerful techniques from machine learning and artificial intelligence to generate highly deceptive visual and audio content.

Neural networks are one of the most beautiful programming paradigms ever invented. In the conventional approach to programming, we tell the computer what to do, breaking big problems up into many small, precisely defined tasks that the computer can easily perform. By contrast, in a neural network, we don't tell the computer how to solve our problem. Instead, it learns from observational data, figuring out its solution to the problem at hand. Until recently we didn't know how to train neural networks to surpass more traditional approaches, except for a few specialized problems.

Created by Lazy Programmer Inc. English [Auto-generated], Indonesian [Auto-generated], 4 more Created by Lazy Programmer Inc. It's hard to believe it's been been over a year since I released my first course on Deep Learning with NLP (natural language processing). A lot of cool stuff has happened since then, and I've been deep in the trenches learning, researching, and accumulating the best and most useful ideas to bring them back to you. So what is this course all about, and how have things changed since then? In previous courses, you learned about some of the fundamental building blocks of Deep NLP.

Traffic flow prediction is a crucial task in enabling efficient intelligent transportation systems and smart cities. Although there has been rapid progress in this area in the last few years, given the major advances of deep learning techniques, it remains a challenging task because of the inherent periodic characteristics of traffic flow sequence. To incorporate the periodicity in the prediction process, existing methods have observed three components separately as the input of prediction models, i.e., the closeness, period, and trend components. The long term relation of these components has not been fully addressed. In this paper, we present a novel architecture, TRAILER (TRAnsformer-based tIme-wise Long tErm Relation modeling), to predict traffic flows more effectively. First, we explicitly design a Transformer based long term relation prediction module to model the long term relation and predict the periodic relation to be used for the downstream task. Second, we propose a consistency module at the target time interval, in order to model the consistency of the predicted periodic relation and the relation inferred from the predicted traffic flow tensor. Finally, based on the consistency module, we introduce a consistency loss to stabilize the training process and further improve the prediction performance. Through extensive experiments, we show the superiority of the proposed method on three real-world datasets and the effectiveness of each module in TRAILER.

The performance of Human Activity Recognition (HAR) models, particularly deep neural networks, is highly contingent upon the availability of the massive amount of annotated training data which should be sufficiently labeled. Though, data acquisition and manual annotation in the HAR domain are prohibitively expensive due to skilled human resource requirements in both steps. Hence, domain adaptation techniques have been proposed to adapt the knowledge from the existing source of data. More recently, adversarial transfer learning methods have shown very promising results in image classification, yet limited for sensor-based HAR problems, which are still prone to the unfavorable effects of the imbalanced distribution of samples. This paper presents a novel generic and robust approach for semi-supervised domain adaptation in HAR, which capitalizes on the advantages of the adversarial framework to tackle the shortcomings, by leveraging knowledge from annotated samples exclusively from the source subject and unlabeled ones of the target subject. Extensive subject translation experiments are conducted on three large, middle, and small-size datasets with different levels of imbalance to assess the robustness and effectiveness of the proposed model to the scale as well as imbalance in the data. The results demonstrate the effectiveness of our proposed algorithms over state-of-the-art methods, which led in up to 13%, 4%, and 13% improvement of our high-level activities recognition metrics for Opportunity, LISSI, and PAMAP2 datasets, respectively. The LISSI dataset is the most challenging one owing to its less populated and imbalanced distribution. Compared to the SA-GAN adversarial domain adaptation method, the proposed approach enhances the final classification performance with an average of 7.5% for the three datasets, which emphasizes the effectiveness of micro-mini-batch training.

We introduce PerSenT, a dataset of crowd-sourced annotations of the sentiment expressed by the authors towards the main entities in news articles. The dataset also includes paragraph-level sentiment annotations to provide more fine-grained supervision for the task. Our benchmarks of multiple strong baselines show that this is a difficult classification task. The results also suggest that simply fine-tuning document-level representations from BERT isn't adequate for this task. Making paragraph-level decisions and aggregating them over the entire document is also ineffective. We present empirical and qualitative analyses that illustrate the specific challenges posed by this dataset. We release this dataset with 5.3k documents and 38k paragraphs covering 3.2k unique entities as a challenge in entity sentiment analysis.

Deep learning has proved an effective means to capture the non-linear associations of user preferences. However, the main drawback of existing deep learning architectures is that they follow a fixed recommendation strategy, ignoring users' real time-feedback. Recent advances of deep reinforcement strategies showed that recommendation policies can be continuously updated while users interact with the system. In doing so, we can learn the optimal policy that fits to users' preferences over the recommendation sessions. The main drawback of deep reinforcement strategies is that are based on predefined and fixed neural architectures. To shed light on how to handle this issue, in this study we first present deep reinforcement learning strategies for recommendation and discuss the main limitations due to the fixed neural architectures. Then, we detail how recent advances on progressive neural architectures are used for consecutive tasks in other research domains. Finally, we present the key challenges to fill the gap between deep reinforcement learning and adaptive neural architectures. We provide guidelines for searching for the best neural architecture based on each user feedback via reinforcement learning, while considering the prediction performance on real-time recommendations and the model complexity.

In this comprehensive review, we describe a new mathematical problem in artificial intelligence (AI) from a mathematical modeling perspective, following the philosophy stated by Rudolf E. Kalman that "Once you get the physics right, the rest is mathematics". The new problem is called "Generalized Constraints (GCs)", and we adopt GCs as a general term to describe any type of prior information in modelings. To understand better about GCs to be a general problem, we compare them with the conventional constraints (CCs) and list their extra challenges over CCs. In the construction of AI machines, we basically encounter more often GCs for modeling, rather than CCs with well-defined forms. Furthermore, we discuss the ultimate goals of AI and redefine transparent, interpretable, and explainable AI in terms of comprehension levels about machines. We review the studies in relation to the GC problems although most of them do not take the notion of GCs. We demonstrate that if AI machines are simplified by a coupling with both knowledge-driven submodel and data-driven submodel, GCs will play a critical role in a knowledge-driven submodel as well as in the coupling form between the two submodels. Examples are given to show that the studies in view of a generalized constraint problem will help us perceive and explore novel subjects in AI, or even in mathematics, such as generalized constraint learning (GCL).

Deep learning (DL) models for disease classification or segmentation from medical images are increasingly trained using transfer learning (TL) from unrelated natural world images. However, shortcomings and utility of TL for specialized tasks in the medical imaging domain remain unknown and are based on assumptions that increasing training data will improve performance. We report detailed comparisons, rigorous statistical analysis and comparisons of widely used DL architecture for binary segmentation after TL with ImageNet initialization (TII-models) with supervised learning with only medical images(LMI-models) of macroscopic optical skin cancer, microscopic prostate core biopsy and Computed Tomography (CT) DICOM images. Through visual inspection of TII and LMI model outputs and their Grad-CAM counterparts, our results identify several counter intuitive scenarios where automated segmentation of one tumor by both models or the use of individual segmentation output masks in various combinations from individual models leads to 10% increase in performance. We also report sophisticated ensemble DL strategies for achieving clinical grade medical image segmentation and model explanations under low data regimes. For example; estimating performance, explanations and replicability of LMI and TII models described by us can be used for situations in which sparsity promotes better learning. A free GitHub repository of TII and LMI models, code and more than 10,000 medical images and their Grad-CAM output from this study can be used as starting points for advanced computational medicine and DL research for biomedical discovery and applications.