These are some of the terms used to describe artificial intelligence. However, as government leaders and businesses grapple with the idea of harnessing the power of AI, they often forget one key element -- innovation is only as good as its application. You might have a fantastic concept, but without the proper execution, it remains just that -- a concept instead of something you're able to benefit from. So, it's about time we changed our focus from the theory behind artificial intelligence to AI-powered systems. Deep neural networks, also known as deep learning, emulate human brain functioning, and "learn" from audio, images, and text.

This tutorial is an excerpt from "Deep Learning Essentials" by Wei Di, Anurag Bhardwaj, Jianing Wei and published by Packt. Use the code ORKDNA10 at checkout to get the recommended eBook for just $10 until May 31, 2018. Like in many other cases, the representation of the data, which is how the information is encoded and shown to machine learning algorithms, is often the most important and fundamental part in all pipelines of learning or AI. The effectiveness and scalability of the representation largely determine for the performance of the downstream machine learning model and application. As mentioned in the previous section, traditional NLP often uses one-hot encoding to represent the word in a fixed vocabulary and uses a BoW to represent documents.

Artificial intelligence (AI) stands out as a transformational technology of our digital age -- and its practical application throughout the economy is growing apace. Neural networks are a subset of machine learning techniques, loosely modelling the way that neurons interact in the brain. AI practitioners refer to these techniques as "deep learning…". Deep learning requires thousands of data records for models to become relatively good at classification tasks and, in some cases, millions for them to perform at the level of humans. By one estimate, a supervised deep-learning algorithm will achieve acceptable performance with around 5,000 labelled examples per category and will match or exceed human-level performance when trained with a data set containing at least 10 million labelled examples.

With the recent availability of Electronic Health Records (EHR) and great opportunities they offer for advancing medical informatics, there has been growing interest in mining EHR for improving quality of care. Disease diagnosis due to its sensitive nature, huge costs of error, and complexity has become an increasingly important focus of research in past years. Existing studies model EHR by capturing co-occurrence of clinical events to learn their latent embeddings. However, relations among clinical events carry various semantics and contribute differently to disease diagnosis which gives precedence to a more advanced modeling of heterogeneous data types and relations in EHR data than existing solutions. To address these issues, we represent how high-dimensional EHR data and its rich relationships can be suitably translated into HeteroMed, a heterogeneous information network for robust medical diagnosis. Our modeling approach allows for straightforward handling of missing values and heterogeneity of data. HeteroMed exploits metapaths to capture higher level and semantically important relations contributing to disease diagnosis. Furthermore, it employs a joint embedding framework to tailor clinical event representations to the disease diagnosis goal. To the best of our knowledge, this is the first study to use Heterogeneous Information Network for modeling clinical data and disease diagnosis. Experimental results of our study show superior performance of HeteroMed compared to prior methods in prediction of exact diagnosis codes and general disease cohorts. Moreover, HeteroMed outperforms baseline models in capturing similarities of clinical events which are examined qualitatively through case studies.

Expert diagnostic support systems have been extensively studied. The practical application of these systems in real-world scenarios have been somewhat limited due to well-understood shortcomings such as extensibility. More recently, machine learned models for medical diagnosis have gained momentum since they can learn and generalize patterns found in very large datasets like electronic health records. These models also have shortcomings. In particular, there is no easy way to incorporate prior knowledge from existing literature or experts. In this paper, we present a method to merge both approaches by using expert systems as generative models that create simulated data on which models can be learned. We demonstrate that such a learned model not only preserve the original properties of the expert systems but also addresses some of their limitations. Furthermore, we show how this approach can also be used as the starting point to combine expert knowledge with knowledge extracted from other data sources such as electronic health records.

Multi-modal data is becoming more common than before because of big data issues. Finding the semantically equal or similar objects from different data sources(called entity resolution) is one of the heart problem of multi-modal task. Current models for solving this problem usually needs much paired data to find the latent correlation between multi-modal data, which is of high cost. A new kind latent correlation is proposed in this article. With the correlation, multi-modal objects can be uniformly represented in a commonly shard space. A classifying based model is designed for multi-modal entity resolution task. With the proposed method, the demand of training data can be decreased much.

Right: A picture of the prototype which has been retrofitted into a typical clinical-grade light microscope. Applications of deep learning in medical disciplines including ophthalmology, dermatology, radiology and pathology have recently shown great promise to increase both the accuracy and availability of high-quality healthcare. To further this technology, Google researchers have developed a tool that combines augmented reality with a deep learning neural network to provide pathologists with help in spotting cancerous cells on slides under a microscope. The prototype Augmented Reality Microscope (ARM) platform consists of a modified light microscope that enables real-time image analysis and presentation of the results of machine learning algorithms directly into the field of view. The ARM can be retrofitted into existing light microscopes found in hospitals and clinics by using low-cost, readily available components, and without the need for whole slide digital versions of the tissue being analyzed.

A.I. is a relatively well-known term in the modern world but that doesn't necessarily mean that it's well-understood by the general public. That's thanks in no small part to the widespread use of narrow A.I. – that's artificial intelligence with strict operating parameters that nearly everybody uses at one point or another. In fact, in the strictest sense, it's probably safe to say that the current forms of A.I. aren't consistent with what defines a "true" A.I. The technology would need to become as adaptable and "smart" as humans are to reach that point. However, that particular definition is also all too subjective and the A.I. that does exist is nothing to scoff at. DeepMind, for example, has only been in existence since 2010 and was only acquired by Google in 2014.

We fell for Recurrent neural networks (RNN), Long-short term memory (LSTM), and all their variants. Now it is time to drop them! It is the year 2014 and LSTM and RNN make a great come-back from the dead. But we were all young and unexperienced. For a few years this was the way to solve sequence learning, sequence translation (seq2seq), which also resulted in amazing results in speech to text comprehension and the raise of Siri, Cortana, Google voice assistant, Alexa.

Artificial Intelligence (AI) is the new buzz word. We all have heard and read that it will change the world. However, most articles fall short on explaining how exactly AI algorithms can be used to solve real-world problems. This series is my attempt at bridging the gap between technical AI and applications of AI. For this series, I will restrict to Machine Learning (ML) algorithms which is a section of AI where we let machines learn from data. My focus will be to explore how ML algorithms can be used to model and predict human buying behavior.