Early recognition of abnormal rhythm in ECG signals is crucial for monitoring or diagnosing patients' cardiac conditions and increasing the success rate of the treatment. Classifying abnormal rhythms into fine-grained categories is very challenging due to the the broad taxonomy of rhythms, noises and lack of real-world data and annotations from large number of patients. This paper presents a new ECG classification method based on Deep Convolutional Neural Networks (DCNN) and online decision fusion. Different from previous methods which utilize hand-crafted features or learn features from the original signal domain, the proposed DCNN based method learns features and classifiers from the time-frequency domain in an end-to-end manner. First, the ECG wave signal is transformed to time-frequency domain by using Short-Time Fourier Transform. Next, specific DCNN models are trained on ECG samples of specific length. Finally, an online decision fusion method is proposed to fuse past and current decisions from different models into a more accurate one. Experimental results on both synthetic and real-world ECG datasets convince the effectiveness and efficiency of the proposed method.

We propose a principle for exploring context in machine learning models. Starting with a simple assumption that each observation (random variables) may or may not depend on its context (conditional variables), a conditional probability distribution is decomposed into two parts: context-free and context-sensitive. Then by employing the log-linear word production model for relating random variables to their embedding space representation and making use of the convexity of natural exponential function, we show that the embedding of an observation can also be decomposed into a weighted sum of two vectors, representing its context-free and context-sensitive parts, respectively. This simple treatment of context provides a unified view of many existing deep learning models, leading to revisions of these models able to achieve significant performance boost. Specifically, our upgraded version of a recent sentence embedding model (Arora et al., 2017) not only outperforms the original one by a large margin, but also leads to a new, principled approach for compositing the embeddings of bag-of-words features, as well as a new architecture for modeling attention in deep neural networks. More surprisingly, our new principle provides a novel understanding of the gates and equations defined by the long short term memory (LSTM) model, which also leads to a new model that is able to converge significantly faster and achieve much lower prediction errors. Furthermore, our principle also inspires a new type of generic neural network layer that better resembles real biological neurons than the traditional linear mapping plus nonlinear activation based architecture. Its multi-layer extension provides a new principle for deep neural networks which subsumes residual network (ResNet) as its special case, and its extension to convolutional neutral network model accounts for irrelevant input (e.g., background in an image) in addition to filtering. Our models are validated through a series of benchmark datasets and we show that in many cases, simply replacing existing layers with our context-aware counterparts is sufficient to significantly improve the results.

Deep neural networks (DNNs) have been widely used in the fields such as natural language processing, computer vision and image recognition. But several studies have been shown that deep neural networks can be easily fooled by artificial examples with some perturbations, which are widely known as adversarial examples. Adversarial examples can be used to attack deep neural networks or to improve the robustness of deep neural networks. A common way of generating adversarial examples is to first generate some noises and then add them into original examples. In practice, different examples have different noise-sensitive. To generate an effective adversarial example, it may be necessary to add a lot of noise to low noise-sensitive example, which may make the adversarial example meaningless. In this paper, we propose a noise-sensitivity-analysis-based test prioritization technique to pick out examples by their noise sensitivity. We construct an experiment to validate our approach on four image sets and two DNN models, which shows that examples are sensitive to noise and our method can effectively pick out examples by their noise sensitivity.

Providing systems the ability to relate linguistic and visual content is one of the hallmarks of computer vision. Tasks such as image captioning and retrieval were designed to test this ability, but come with complex evaluation measures that gauge various other abilities and biases simultaneously. This paper presents an alternative evaluation task for visual-grounding systems: given a caption the system is asked to select the image that best matches the caption from a pair of semantically similar images. The system's accuracy on this Binary Image SelectiON (BISON) task is not only interpretable, but also measures the ability to relate fine-grained text content in the caption to visual content in the images. We gathered a BISON dataset that complements the COCO Captions dataset and used this dataset in auxiliary evaluations of captioning and caption-based retrieval systems. While captioning measures suggest visual grounding systems outperform humans, BISON shows that these systems are still far away from human performance.

The paper presents an approach to build a question and answer system that is capable of processing the information in a large dataset and allows the user to gain knowledge from this dataset by asking questions in natural language form. Key content of this research covers four dimensions which are; Corpus Preprocessing, Question Preprocessing, Deep Neural Network for Answer Extraction and Answer Generation. The system is capable of understanding the question, responds to the user's query in natural language form as well. The goal is to make the user feel as if they were interacting with a person than a machine.

Document classification is a challenging task with important applications. Deep learning approaches to the problem have gained much attention. Despite the progress, the proposed models do not incorporate the knowledge of the document structure in the architecture efficiently and not take into account the contexting dependent importance of words and sentences. In this paper, we propose a new approach based on convolutional neural networks, gated recurrent units and attention mechanisms for document classification tasks. The datasets IMDB Movie Reviews and Yelp were used in experiments. The proposed method improves the results of current attention-based approaches

The flaw in our approach lies in the ways we are developing AI systems for commercial application. We are creating algorithms that are used to detect patterns in data, and we often use a top-down approach. As a recent WIRED cover story noted, our AI systems have become increasingly dependent on deep learning, a type of machine learning technique that has evolved over the past decade. The central challenge of deep learning when applied to pattern recognition is that it is beginning to reach a plateau of usefulness for certain classes of problems. Such models are entirely data-dependent with no evidentiary logic presented as part of their output - which means the AI is not able to intuit to solve certain problems or explain how it reached a conclusion.

The proliferation of data within the military poses a significant challenge for operators interpreting differing data sets into meaningful information upon which to make informed and timely decisions. Artificial Intelligence capabilities are developing at pace and can present opportunities through Deep Learning for operators and decision makers to interpret vast, disparate data sets concurrently. The Defence and Security Accelerator (DASA) has funded two projects led by Montvieux, in excess of £500,000, following a DASA themed competition to find new technologies, processes and ideas to'Revolutionise the human information relationship for Defence'. The Prediction Toolset is a Deep Learning based Artificial Intelligence capability that uses current and historical information to predict the change of control on the ground, in both space and time, between opposing groups fighting within an operational theatre. This capability provides foresight to analysts and collection managers, enabling them to proactively anticipate future events on the ground, thereby enhancing the protection of forces and improving the efficiency and effectiveness of information collection.

In the last decade, the area of artificial intelligence (AI) has exploded with interesting and promising results. With major achievements in image recognition, speech recognition and highly complex games, AI continues to disrupt society. This blog post will discuss practical applications of AI, optimization and interpretability of deep learning models and reinforcement learning (RL), based on the 2018 REWORK Deep Learning Summit in Toronto. Four software engineers from Knowit had the pleasure of travelling to Canada to attend this conference, and with renowned speakers such as Geoff Hinton attending, it turned out be an insightful experience. Today, the addition of learning is also in place, but due to the non-deterministic nature of the real world, decisions cannot be made purely from the facts that are given. Further development of AI will require improvements in a variety of areas.

Many believed an algorithm would transcend humanity with cognitive awareness. Machines would discern and learn tasks without human intervention and replace workers in droves. They quite literally would be able to "think". Many people even raised the question whether we could have robots for spouses. But I am not talking about today.