The dream of building machines that can do science has inspired scientists for decades. Remarkable advances have been made recently; however, we are still far from achieving this goal. In this paper, we focus on the scientific discovery process where a high level of reasoning and remarkable problem-solving ability are required. We review different machine learning techniques used in scientific discovery with their limitations. We survey and discuss the main principles driving the scientific discovery process. These principles are used in different fields and by different scientists to solve problems and discover new knowledge. We provide many examples of the use of these principles in different fields such as physics, mathematics, and biology. We also review AI systems that attempt to implement some of these principles. We argue that building science discovery machines should be guided by these principles as an alternative to the dominant approach of current AI systems that focuses on narrow objectives. Building machines that fully incorporate these principles in an automated way might open the doors for many advancements.

There has been noticed the prevalent use of the terms AI, Machine Learning and Deep Learning embedded almost very fields now from innovations in the driverless vehicle to games such as poker, automating customer service using Chatbots, anomaly detection of next unavoidable breach in cyber security and opening doors to understanding the large-scale incredibly complex data set that makes up the human genome. There are fundamentally key differences between each type of technology one should understand and know to get familiarize with their use cases and application. In the early era of electronic computers (1940–1950s), the machines were relatively simple, small and slow (compared with today). They were programmed (given recipe-like instructions) to do simple but boring but straightforward arithmetic tasks. The phrase artificial intelligence was coined in 1956 by John McCarthy, who organized an academic conference at Dartmouth dedicated to the topic.

If you're spending months hand-tuning your machine learning model to run well on a particular type of processor, you might be interested in a startup called OctoML, which recently raised $28 million to bring its innovative "Octomizer" to market. Octomizer is the commercial version of Apache TVM, an open source compiler that was created in Professor Luiz Ceze's research project in the Computer Science Department at the University of Washington. Datanami recently caught up with the professor–who is also the CEO of OctoML–to learn about the state of machine learning model compilation in a rapidly changing hardware world. According to Ceze, there is big gap in the MLOps workflow between the completion of the machine learning model by the data scientist or machine learning engineer, and deployment of that model into the real world. Quite often, the services of a software engineer are required to convert the ML model, which is often written in Python using one of the popular frameworks like TensorFlow or PyTorch, into highly optimized C or C that can run on a particular processor.

This book is intended to help management and other interested parties such as engineers, to understand the state of the art when it comes to the intersection between AI and Industry 4.0 and get them to realise the huge possibilities which can be unleashed by the intersection of these two fields. We have heard a lot about Industry 4.0, but most of the time, it focuses mainly on automation. In this book, the authors are going a step further by exploring advanced applications of Artificial Intelligence (AI) techniques, ranging from the use of deep learning algorithms in order to make predictions, up to an implementation of a full-blown Digital Triplet system. The scope of the book is to showcase what is currently brewing in the labs with the hope of migrating these technologies towards the factory floors. Chairpersons and CEOs must read these papers if they want to stay at the forefront of the game, ahead of their competition, while also saving huge sums of money in the process.

The modern AI revolution began during an obscure research contest. It was 2012, the third year of the annual ImageNet competition, which challenged teams to build computer vision systems that would recognize 1,000 objects, from animals to landscapes to people. In the first two years, the best teams had failed to reach even 75% accuracy. But in the third, a band of three researchers--a professor and his students--suddenly blew past this ceiling. They won the competition by a staggering 10.8 percentage points.

AI is transforming the practice of medicine. It's helping doctors diagnose patients more accurately, make predictions about patients' future health, and recommend better treatments. As an AI practitioner, you have the opportunity to join in this transformation of modern medicine. If you're already familiar with some of the math and coding behind AI algorithms, and are eager to develop your skills further to tackle challenges in the healthcare industry, then this specialization is for you. No prior medical expertise is required!

This paper proposes a novel knowledge distillation-based learning method to improve the classification performance of convolutional neural networks (CNNs) without a pre-trained teacher network, called exit-ensemble distillation. Our method exploits the multi-exit architecture that adds auxiliary classifiers (called exits) in the middle of a conventional CNN, through which early inference results can be obtained. The idea of our method is to train the network using the ensemble of the exits as the distillation target, which greatly improves the classification performance of the overall network. Our method suggests a new paradigm of knowledge distillation; unlike the conventional notion of distillation where teachers only teach students, we show that students can also help other students and even the teacher to learn better. Experimental results demonstrate that our method achieves significant improvement of classification performance on various popular CNN architectures (VGG, ResNet, ResNeXt, WideResNet, etc.). Furthermore, the proposed method can expedite the convergence of learning with improved stability. Our code will be available on Github.

The graph data structure is a staple in mathematics, yet graph-based machine learning is a relatively green field within the domain of data science. Recent advances in graph-based ML and open source implementations of relevant algorithms are allowing researchers to apply methods created in academia to real-world datasets. The goal of this project was to utilize a popular graph machine learning framework, GraphSAGE, to predict mergers and acquisitions (M&A) of enterprise companies. The results were promising, as the model predicted with 81.79% accuracy on a validation dataset. Given the abundance of data sources and algorithmic decision making within financial data science, graph-based machine learning offers a performant, yet non-traditional approach to generating alpha.

Video-based person re-identification (Re-ID) aims to retrieve video sequences of the same person under non-overlapping cameras. Previous methods usually focus on limited views, such as spatial, temporal or spatial-temporal view, which lack of the observations in different feature domains. To capture richer perceptions and extract more comprehensive video representations, in this paper we propose a novel framework named Trigeminal Transformers (TMT) for video-based person Re-ID. More specifically, we design a trigeminal feature extractor to jointly transform raw video data into spatial, temporal and spatial-temporal domain. Besides, inspired by the great success of vision transformer, we introduce the transformer structure for video-based person Re-ID. In our work, three self-view transformers are proposed to exploit the relationships between local features for information enhancement in spatial, temporal and spatial-temporal domains. Moreover, a cross-view transformer is proposed to aggregate the multi-view features for comprehensive video representations. The experimental results indicate that our approach can achieve better performance than other state-of-the-art approaches on public Re-ID benchmarks. We will release the code for model reproduction.

Interest in physical therapy and individual exercises such as yoga/dance has increased alongside the well-being trend. However, such exercises are hard to follow without expert guidance (which is impossible to scale for personalized feedback to every trainee remotely). Thus, automated pose correction systems are required more than ever, and we introduce a new captioning dataset named FixMyPose to address this need. We collect descriptions of correcting a "current" pose to look like a "target" pose (in both English and Hindi). The collected descriptions have interesting linguistic properties such as egocentric relations to environment objects, analogous references, etc., requiring an understanding of spatial relations and commonsense knowledge about postures. Further, to avoid ML biases, we maintain a balance across characters with diverse demographics, who perform a variety of movements in several interior environments (e.g., homes, offices). From our dataset, we introduce the pose-correctional-captioning task and its reverse target-pose-retrieval task. During the correctional-captioning task, models must generate descriptions of how to move from the current to target pose image, whereas in the retrieval task, models should select the correct target pose given the initial pose and correctional description. We present strong cross-attention baseline models (uni/multimodal, RL, multilingual) and also show that our baselines are competitive with other models when evaluated on other image-difference datasets. We also propose new task-specific metrics (object-match, body-part-match, direction-match) and conduct human evaluation for more reliable evaluation, and we demonstrate a large human-model performance gap suggesting room for promising future work. To verify the sim-to-real transfer of our FixMyPose dataset, we collect a set of real images and show promising performance on these images.