Keras is a Python library for deep learning that wraps the efficient numerical libraries TensorFlow and Theano. Keras allows you to quickly and simply design and train neural network and deep learning models. In this post you will discover how to effectively use the Keras library in your machine learning project by working through a binary classification project step-by-step. Binary Classification Worked Example with the Keras Deep Learning Library Photo by Mattia Merlo, some rights reserved. The dataset we will use in this tutorial is the Sonar dataset.

Insilico Medicine and Life Extension announced today an exclusive collaboration to identify novel biomarkers of human aging through the use of big-data analytics and AI, with the ultimate goal of discovery and formulation of nutrients to support health and longevity. Insilico Medicine* is a big-data analytics company specializing in applying advances in deep learning to discovery of biomarkers and drugs. Life Extension**, a Florida-based organization established in the early 1980s, is a dietary-supplement innovator dedicated to extending healthy human longevity. Insilico Medicine will focus on applying advanced signaling pathway activation analysis techniques and deep-learning algorithms to find nutraceuticals that mimic the tissue-specific transcriptional response of many known interventions and pathways associated with health and longevity. Life Extension will use this information to develop novel nutraceutical products to support health and longevity, such as "geroprotectors" -- precision natural organic small-molecule formulations that slow down or even reverse age-associated conditions and damage.

Objective: Patient notes in electronic health records (EHRs) may contain critical information for medical investigations. However, the vast majority of medical investigators can only access de-identified notes, in order to protect the confidentiality of patients. In the United States, the Health Insurance Portability and Accountability Act (HIPAA) defines 18 types of protected health information (PHI) that needs to be removed to de-identify patient notes. Manual de-identification is impractical given the size of EHR databases, the limited number of researchers with access to the non-de-identified notes, and the frequent mistakes of human annotators. A reliable automated de-identification system would consequently be of high value. Materials and Methods: We introduce the first de-identification system based on artificial neural networks (ANNs), which requires no handcrafted features or rules, unlike existing systems. We compare the performance of the system with state-of-the-art systems on two datasets: the i2b2 2014 de-identification challenge dataset, which is the largest publicly available de-identification dataset, and the MIMIC de-identification dataset, which we assembled and is twice as large as the i2b2 2014 dataset. Results: Our ANN model outperforms the state-of-the-art systems. It yields an F1-score of 97.85 on the i2b2 2014 dataset, with a recall 97.38 and a precision of 97.32, and an F1-score of 99.23 on the MIMIC de-identification dataset, with a recall 99.25 and a precision of 99.06. Conclusion: Our findings support the use of ANNs for de-identification of patient notes, as they show better performance than previously published systems while requiring no feature engineering.

Recently a variety of LSTM-based conditional language models (LM) have been applied across a range of language generation tasks. In this work we study various model architectures and different ways to represent and aggregate the source information in an end-to-end neural dialogue system framework. A method called snapshot learning is also proposed to facilitate learning from supervised sequential signals by applying a companion cross-entropy objective function to the conditioning vector. The experimental and analytical results demonstrate firstly that competition occurs between the conditioning vector and the LM, and the differing architectures provide different trade-offs between the two. Secondly, the discriminative power and transparency of the conditioning vector is key to providing both model interpretability and better performance. Thirdly, snapshot learning leads to consistent performance improvements independent of which architecture is used.

One major challenge in training Deep Neural Networks is preventing overfitting. Many techniques such as data augmentation and novel regularizers such as Dropout have been proposed to prevent overfitting without requiring a massive amount of training data. In this work, we propose a new regularizer called DeCov which leads to significantly reduced overfitting (as indicated by the difference between train and val performance), and better generalization. Our regularizer encourages diverse or non-redundant representations in Deep Neural Networks by minimizing the cross-covariance of hidden activations. This simple intuition has been explored in a number of past works but surprisingly has never been applied as a regularizer in supervised learning. Experiments across a range of datasets and network architectures show that this loss always reduces overfitting while almost always maintaining or increasing generalization performance and often improving performance over Dropout.

'He is standing in the stars and sitting on the floor' – it's one of many bizarre lines from a new science fiction screenplay called Sunspring, written entirely by an AI. The short film is barely nine minutes long and is strangely captivating as it gravitates between dark and cryptic to outright hilarious, with blocks of nonsensical dialogue. Sunspring was created for the annual film festival Sci-Fi London, and debuted today on Ars Technica. 'He is standing in the stars and sitting on the floor' – it's one of many bizarre lines from a new science fiction screenplay called Sunspring, written entirely by an AI. To produce the film, director Oscar Sharp and collaborator Ross Goodwin, an NYU AI researcher, fed dozens of scripts to a long short-term memory (LSTM) recurrent neural network that has named itself Benjamin.

Recently, neural networks have become the tool of choice for a variety of tough computer-science problems: Facebook uses them to identify faces in photos, Google uses them to identify everything in photos. Apple uses them to figure out what you're saying to Siri, and IBM uses them for operationalizing business unit synergies. Can neural networks help you find the emoji when you really need it? This post will outline some of the engineering behind Dango, allowing us to automatically learn from hundreds of millions of real-world uses of emoji, and distill this down to a tool small and fast enough to predict emoji for you in real time on your phone. Dango is a floating assistant that runs on your phone and predicts emoji, stickers and GIFs based on what you and your friends are writing in any app.

SF Bay ACM Members: We NEED you to attend! Chapter Elections will be briefly held at the beginning of this meeting. In this talk, Arno Candel presents a brief history of AI and how Deep Learning and Machine Learning techniques are transforming our everyday lives. Arno will introduce H2O, a scalable open-source machine learning platform, and show live demos on how to train sophisticated machine learning models on large distributed datasets. He will show how data scientists and application developers can use the Flow GUI, R, Python, Java, Scala, JavaScript and JSON to build smarter applications, and how to take them to production.

That's an interesting question, and I try to answer this in a very general way. In essence, deep learning offers a set of techniques and algorithms that help us to parameterize deep neural network structures -- artificial neural networks with many hidden layers and parameters. One of the key ideas behind deep learning is to extract high level features from the given dataset. Thereby, deep learning aims to overcome the challenge of the often tedious feature engineering task and helps with parameterizing traditional neural networks with many layers. Now, to introduce deep learning, let us take a look at a more concrete example involving multi-layer perceptrons (MLPs).

Machine learning and computer vision methods have recently received a lot of attention, in particular when it comes to data analytics. The success of deep neural networks that can help cars drive autonomously and make smartphones recognize speech and translate text attests to the value of using machine learning methods to tackle complex real-world problems. A further prominent example is the success of Google's AlphaGo AI that defeated the world champion Lee Sedol in playing Go. This is remarkable in particular since Go has previously been considered as one of the most complex games due to the larger number of game states. As the amount of data collected by cameras and scientific instruments continues to rise, automated analysis methods will become ever more important in the future. Reappearing workflows, such as the segmentation of structures, will likely be either fully automated or supported by computers.