Use of medical data, also known as electronic health records, in research helps develop and advance medical science. However, protecting patient confidentiality and identity while using medical data for analysis is crucial. Medical data can be in the form of tabular structures (i.e. tables), free-form narratives, and images. This study focuses on medical data in the free form longitudinal text. De-identification of electronic health records provides the opportunity to use such data for research without it affecting patient privacy, and avoids the need for individual patient consent. In recent years there is increasing interest in developing an accurate, robust and adaptable automatic de-identification system for electronic health records. This is mainly due to the dilemma between the availability of an abundance of health data, and the inability to use such data in research due to legal and ethical restrictions. De-identification tracks in competitions such as the 2014 i2b2 UTHealth and the 2016 CEGS N-GRID shared tasks have provided a great platform to advance this area. The primary reasons for this include the open source nature of the dataset and the fact that raw psychiatric data were used for 2016 competitions. This study focuses on noticeable trend changes in the techniques used in the development of automatic de-identification for longitudinal clinical narratives. More specifically, the shift from using conditional random fields (CRF) based systems only or rules (regular expressions, dictionary or combinations) based systems only, to hybrid models (combining CRF and rules), and more recently to deep learning based systems. We review the literature and results that arose from the 2014 and the 2016 competitions and discuss the outcomes of these systems. We also provide a list of research questions that emerged from this survey.

Humans spend a remarkable fraction of waking life engaged in acts of "mental time travel". We dwell on our actions in the past and experience satisfaction or regret. More than merely autobiographical storytelling, we use these event recollections to change how we will act in similar scenarios in the future. This process endows us with a computationally important ability to link actions and consequences across long spans of time, which figures prominently in addressing the problem of long-term temporal credit assignment; in artificial intelligence (AI) this is the question of how to evaluate the utility of the actions within a long-duration behavioral sequence leading to success or failure in a task. Existing approaches to shorter-term credit assignment in AI cannot solve tasks with long delays between actions and consequences. Here, we introduce a new paradigm for reinforcement learning where agents use recall of specific memories to credit actions from the past, allowing them to solve problems that are intractable for existing algorithms. This paradigm broadens the scope of problems that can be investigated in AI and offers a mechanistic account of behaviors that may inspire computational models in neuroscience, psychology, and behavioral economics.

On the one hand, a trellis network is a temporal convolutional network with special structure, characterized by weight tying across depth and direct injection of the input into deep layers. On the other hand, we show that truncated recurrent networks are equivalent to trellis networks with special sparsity structure in their weight matrices. Thus trellis networks with general weight matrices generalize truncated recurrent networks. We leverage these connections to design high-performing trellis networks that absorb structural and algorithmic elements from both recurrent and convolutional models. Experiments demonstrate that trellis networks outperform the current state of the art on a variety of challenging benchmarks, including word-level language modeling on Penn Treebank and WikiText-103, character-level language modeling on Penn Treebank, and stress tests designed to evaluate long-term memory retention. The code is available here. What is the best architecture for sequence modeling? Recent research has produced significant progress on multiple fronts. Recurrent networks, such as LSTMs, continue to be optimized and extended (Merity et al., 2018b; Melis et al., 2018; Y ang et al., 2018; Trinh et al., 2018). Temporal convolutional networks have demonstrated impressive performance, particularly in modeling long-range context (van den Oord et al., 2016; Dauphin et al., 2017; Bai et al., 2018). And architectures based on self-attention are gaining ground (V aswani et al., 2017; Santoro et al., 2018). In this paper, we introduce a new architecture for sequence modeling, the Trellis Network. We aim to both improve empirical performance on sequence modeling benchmarks and shed light on the relationship between two existing model families: recurrent and convolutional networks.

In the legal domain it is important to differentiate between words in general, and afterwards to link the occurrences of the same entities. The topic to solve these challenges is called Named-Entity Linking (NEL). Current supervised neural networks designed for NEL use publicly available datasets for training and testing. However, this paper focuses especially on the aspect of applying transfer learning approach using networks trained for NEL to legal documents. Experiments show consistent improvement in the legal datasets that were created from the European Union law in the scope of this research. Using transfer learning approach, we reached F1-score of 98.90\% and 98.01\% on the legal small and large test dataset.

With a technology as impactful as machine learning (ML), it can be difficult to avoid hyperbole. Sure, billions of dollars in investment are pouring into ML projects. Yes, machine learning is a centerpiece of digital transformation strategies. And, to be certain, machine learning is often what people are talking about when they use the umbrella term "AI." So it's worth taking the time to look at real-world ML capabilities being developed and deployed at digitally nimble companies around the globe.

In Transfer Learning, the knowledge of an already trained Machine Learning model is applied to a different but related problem. For example, if you trained a simple classifier to predict whether an image contains a backpack, you could use the knowledge that the model gained during its training to recognize other objects like sunglasses. With transfer learning, we basically try to exploit what has been learned in one task to improve generalization in another. We transfer the weights that a Network has learned at Task A to a new Task B. The general idea is to use knowledge, that a model has learned from a task where a lot of labeled training data is available, in a new task where we don't have a lot of data. Instead of starting the learning process from scratch, you start from patterns that have been learned from solving a related task.

Hardly could anyone find a point at the Heidelberg Laurate Forum space-time without hearing about Artificial Intelligence, Machine Learning and Deep Learning. The truth is that the majority of mathematician lecturers were fascinated by the allure of algorithms. The most conservative ones have already transformed computing machines into self-developing systems functioning in a limited field of knowledge while some brave ones design broader AI applications. One of the few exceptions to the rule was Sir Michael Francis Atiyah. Defying the skepticism of his peers he claimed to have solved the Riemann Hypothesis which has remained unsolved for more than 160 years, making it a million dollar problem.

The minimum requirements to successfully apply deep learning depends on the problem you're trying to solve. In contrast to static, benchmark datasets like MNIST and CIFAR-10, real-world data is messy, varied and evolving, and that is the data practical deep learning solutions must deal with. Deep learning can be applied to any data type. The data types you work with, and the data you gather, will depend on the problem you're trying to solve. Deep learning can solve almost any problem of machine perception, including classifying data, clustering it, or making predictions about it.

A 2009 study of 102 breast cancer patients at two Boston health centers found that one in four were affected by the "process of care" failures such as inadequate physical examinations and incomplete diagnostic tests. That's one of the reasons that of the half a million deaths worldwide caused by breast cancer, an estimated 90 percent are the result of metastasis. But researchers at the Naval Medical Center San Diego and Google AI, a division within Google dedicated to artificial intelligence (AI) research, have developed a promising solution employing cancer-detecting algorithms that autonomously evaluate lymph node biopsies. Their AI system -- dubbed Lymph Node Assistant, or LYNA -- is described in a paper titled "Artificial Intelligence-Based Breast Cancer Nodal Metastasis Detection," published in The American Journal of Surgical Pathology. In tests, it achieved an area under the receiver operating characteristic (AUC) -- a measure of detection accuracy -- of 99 percent.

Summary: What comes next after Deep Learning? How do we get to Artificial General Intelligence? Adversarial Machine Learning is an emerging space that points to that direction and shows that AGI is closer than we think. Deep Learning, Convolutional Neural Nets (CNNs) have given us dramatic improvements in image, speech, and text recognition over the last two years. They suffer from the flaw however that they can be easily fooled by the introduction of even small amounts of noise, random or intentional.