TensorFlow is a deep learning library from Google that is open-source and available on GitHub. TensorFlow excels at numerical computing, which is critical for deep learning. It has a rich set of application programming interfaces in most major languages and environments needed for deep learning projects: Python, C, C, Rust, Haskell, Go, Java, Android, IoS, Mac OS, Windows, Linux, and Raspberry Pi. The primary unit in TensorFlow is a tensor. A tensor consists of a set of primitive values shaped into an array of any number of dimensions.

The machine-learning models scored 82.44 on the Stanford Question Answering Dataset, a large-scale reading comprehension test with more than 100,000 questions, compared with 82.304 by humans. Stanford tests are used by several international universities and global technology firms, including Google, Facebook, IBM and Microsoft, to determine whether their machine learning models are able to answer the questions in the data set. Machines have already bested humans in complex games like chess, where skills such as infallible memory and raw computing power align with the intrinsic capabilities of bots. In December last year (2017), DeepMind, Google's artificial intelligence programme, was able to win a game of chess after first learning how to play the game. Where computers have surpassed human ability before in games of chess by using pre-conditioned programming, DeepMind's AlphaZero program experimented by playing games against itself until it had discerned the effectiveness of all possible moves.

Inundated with more data than humans can analyze, the U.S. military and intelligence community are banking on machine learning and advanced computing technologies to separate the wheat from the chaff. The Defense Department operates more than 11,000 drones that collect hundreds of thousands of hours of video footage every year. "When it comes to intelligence, surveillance and reconnaissance, or ISR, we have more platforms and sensors than at any time in Department of Defense history," said Air Force Lt. Gen. John N.T. "Jack" Shanahan, director for defense intelligence (warfighter support) in the office of the undersecretary of defense for intelligence. "It's an avalanche of data that we are not capable of fully exploiting," he said at a technology conference in Washington, D.C., hosted by Nvidia, a Santa Clara, California-based artificial intelligence computing company. For example, the Pentagon has deployed a wide-area motion imagery sensor that can look at an entire city.

Alibaba has developed an artificial intelligence model that scored better than humans in a Stanford University reading and comprehension test. Alibaba Group Holding (baba) put its deep neural network model through its paces last week, asking the AI to provide exact answers to more than 100,000 questions comprising a quiz that's considered one of the world's most authoritative machine-reading gauges. The model developed by Alibaba's Institute of Data Science of Technologies scored 82.44, edging past the 82.304 that rival humans achieved. Alibaba said it's the first time a machine has out-done a real person in such a contest. Microsoft achieved a similar feat, scoring 82.650 on the same test, but those results were finalized a day after Alibaba's, the company said.

Marc Andreessen had famously said software is eating the world. He probably had Artificial Intelligence (AI) in the back of his mind. In its simplistic form, AI enables a machine to perform human-like tasks, such as image, voice and text recognition, natural language processing and understanding human-like perception. The journey of AI from Expert Systems in the early eighties to Heuristics analysis, machine learning and finally to present day deep learning has been a roller coaster ride. Just a few years back, people thought neural networks were something academicians talked in their leisure time.

Deep learning opens up new worlds of possibility in AI, enabled by advances in computational capacity, the explosion in data, and the advent of deep neural networks. But data is evolving quickly and legacy storage systems are not keeping up.

Survival analysis/time-to-event models are extremely useful as they can help companies predict when a customer will buy a product, churn or default on a loan, and therefore help them improve their ROI. In this paper, we introduce a new method to calculate survival functions using the Multi-Task Logistic Regression (MTLR) model as its base and a deep learning architecture as its core. Based on the Concordance index (C-index) and Brier score, this method outperforms the MTLR in all the experiments disclosed in this paper as well as the Cox Proportional Hazard (CoxPH) model when nonlinear dependencies are found.

Neural network based architectures used for sound recognition are usually adapted from other application domains such as image recognition, which may not harness the time-frequency representation of a signal. The ConditionaL Neural Networks (CLNN) and its extension the Masked ConditionaL Neural Networks (MCLNN) are designed for multidimensional temporal signal recognition. The CLNN is trained over a window of frames to preserve the inter-frame relation, and the MCLNN enforces a systematic sparseness over the network's links that mimics a filterbank-like behavior. The masking operation induces the network to learn in frequency bands, which decreases the network susceptibility to frequency-shifts in time-frequency representations. Additionally, the mask allows an exploration of a range of feature combinations concurrently analogous to the manual handcrafting of the optimum collection of features for a recognition task. MCLNN have achieved competitive performance on the Ballroom music dataset compared to several hand-crafted attempts and outperformed models based on state-of-the-art Convolutional Neural Networks.

The driving force behind the recent success of LSTMs has been their ability to learn complex and non-linear relationships. Consequently, our inability to describe these relationships has led to LSTMs being characterized as black boxes. To this end, we introduce contextual decomposition (CD), an interpretation algorithm for analysing individual predictions made by standard LSTMs, without any changes to the underlying model. By decomposing the output of a LSTM, CD captures the contributions of combinations of words or variables to the final prediction of an LSTM. On the task of sentiment analysis with the Yelp and SST data sets, we show that CD is able to reliably identify words and phrases of contrasting sentiment, and how they are combined to yield the LSTM's final prediction. Using the phrase-level labels in SST, we also demonstrate that CD is able to successfully extract positive and negative negations from an LSTM, something which has not previously been done.