This article was posted by SmileJet on Dev Battles. She's also an artificial intelligence from the movie Her, which imagines how a juiced-up Siri will change our lives. You've heard the jargon: AI, machine learning, deep learning, neural networks, natural language processing. What is artificial intelligence, or AI?

For example, your CAIO will work closely with the CTO and CIO to spearhead new innovative solutions or enhancements to existing products by applying machine learning or deep learning technologies across all aspects of the business.

The terrifying faces may look like creatures from a horror movie, but these digital images were actually generated by artificial intelligence (AI). Pix2pix project has unleashed a new tool that analyzes portraits and fills them in with colors and textures using a technique called generative adversarial networks (GANs). During the process, the system determines if its result match the sketch and will keep repeating the generation process until its own passes as'real' – regardless of how nightmarish the results may look. The terrifying faces may look like creatures from a horror movie, but these digital images were actually generated by artificial intelligence (AI). Users are presented with an input box and an output box and are prompted to draw a face in input, select process and in seconds, the AI will reveal its version of the sketch.

Astronomical image observation is plagued by the fact the the observed image is the result of a convolution between the observed object and what the astronomers call a Point Spread Function (PSF) [1] [2]. In addition to the convolution the image is also polluted by noise that is due to the low energy of the observed objects (photon noise) or to the sensor. The PSF is usually known a priori, thanks to a physical model for the telescope of estimation from known objects. State of the art approaches in astronomical image reconstruction aim at solving an optimization problem that encodes both a data fitting (with observation and PSF) and a regularization term that promote wanted properties in the images [1], [3], [4]. Still, solving a large optimization problem for each new image can be costly and might not be practical in the future. Indeed in the coming years several new generations of instruments such as the Square kilometer Array [5] will provide very large images (both in spatial and spectral dimensions) that will need to be processed efficiently. The most successful image reconstruction approaches rely on convex optimization [3], [4], [6] and are all based on gradient [7] or proximal splitting gradient descent [8]. Interestingly those methods have typically a linear convergence, meaning that the number of iterations necessary to reach a given precision is proportional to the dimension n of the problem [9], where n is the number of pixels.

Advanced driver assistance systems (ADAS) can be significantly improved with effective driver action prediction (DAP). Predicting driver actions early and accurately can help mitigate the effects of potentially unsafe driving behaviors and avoid possible accidents. In this paper, we formulate driver action prediction as a timeseries anomaly prediction problem. While the anomaly (driver actions of interest) detection might be trivial in this context, finding patterns that consistently precede an anomaly requires searching for or extracting features across multi-modal sensory inputs. We present such a driver action prediction system, including a real-time data acquisition, processing and learning framework for predicting future or impending driver action. The proposed system incorporates camera-based knowledge of the driving environment and the driver themselves, in addition to traditional vehicle dynamics. It then uses a deep bidirectional recurrent neural network (DBRNN) to learn the correlation between sensory inputs and impending driver behavior achieving accurate and high horizon action prediction. The proposed system performs better than other existing systems on driver action prediction tasks and can accurately predict key driver actions including acceleration, braking, lane change and turning at durations of 5sec before the action is executed by the driver.

Recurrent Neural Networks (RNNs), which are a powerful scheme for modeling temporal and sequential data need to capture long-term dependencies on datasets and represent them in hidden layers with a powerful model to capture more information from inputs. For modeling long-term dependencies in a dataset, the gating mechanism concept can help RNNs remember and forget previous information. Representing the hidden layers of an RNN with more expressive operations (i.e., tensor products) helps it learn a more complex relationship between the current input and the previous hidden layer information. These ideas can generally improve RNN performances. In this paper, we proposed a novel RNN architecture that combine the concepts of gating mechanism and the tensor product into a single model. By combining these two concepts into a single RNN, our proposed models learn long-term dependencies by modeling with gating units and obtain more expressive and direct interaction between input and hidden layers using a tensor product on 3-dimensional array (tensor) weight parameters. We use Long Short Term Memory (LSTM) RNN and Gated Recurrent Unit (GRU) RNN and combine them with a tensor product inside their formulations. Our proposed RNNs, which are called a Long-Short Term Memory Recurrent Neural Tensor Network (LSTMRNTN) and Gated Recurrent Unit Recurrent Neural Tensor Network (GRURNTN), are made by combining the LSTM and GRU RNN models with the tensor product. We conducted experiments with our proposed models on word-level and character-level language modeling tasks and revealed that our proposed models significantly improved their performance compared to our baseline models.

Recent years have seen a growing interest in understanding deep neural networks from an optimization perspective. It is understood now that converging to low-cost local minima is sufficient for such models to become effective in practice. However, in this work, we propose a new hypothesis based on recent theoretical findings and empirical studies that deep neural network models actually converge to saddle points with high degeneracy. Our findings from this work are new, and can have a significant impact on the development of gradient descent based methods for training deep networks. We validated our hypotheses using an extensive experimental evaluation on standard datasets such as MNIST and CIFAR-10, and also showed that recent efforts that attempt to escape saddles finally converge to saddles with high degeneracy, which we define as `good saddles'. We also verified the famous Wigner's Semicircle Law in our experimental results.

After more than two years of development and a successful limited availability program, legal technology company CS Disco Inc has announced the general availability of DISCO AI. 'Deep learning AI is changing the landscape of innovation in technology. From self-driving cars and home automation, to cancer diagnosis and crime prevention, AI can help solve some of the world's biggest and most complex challenges,' said Neil Etheridge, VP of Marketing at DISCO. 'We wanted to use that technology to simplify and automate the tasks faced today by law firms and corporate legal departments.' While there will be many applications for DISCO AI, initially the focus is to dramatically reduce the time, burden, and cost of identifying evidence in legal document review - a process known as ediscovery. Although older, more rigid technologies and processes - sometimes referred to as TAR (Technology Assisted Review) - have been applied to ediscovery, adoption and results have been limited compared to the potential that AI can deliver.

Are you looking for a pragmatic understanding of machine learning? This is not about research or academics, it's solely about getting your models into production - much like DeepLearni.ng's business model. Deeper than a blog post or typical meetup, we'll explore and discuss the best practices and idioms of the code base across many areas including Spark's JVM Bytecode Generation, CPU-cache-aware Data Structures and Algorithms, Approximations, Probabilistic Data Structures, Shuffle and I/O Optimizations, Streaming Micro-batch Scheduling, Performance Tuning, Configuration, Monitoring, Auto-Scaling, etc. P.S. WE ARE ALWAYS LOOKING FOR GREAT TALENT! va@deeplearni.ng

In 2011, scientists made one of the most important discoveries in the history of AI development. They found that graphics processing units (GPUs) are far better at simulating biological learning than central processing units (CPUs). In retrospect, it seems obvious. Human brains are much more like GPUs than CPUs. Both brains and GPUs rely on parallel processing that simulates and predicts real world physics. In light of this, AI developers created powerful deep neural networks (DNNs) that emulate human brain function.