Compositionality, generalization, and learning from a few examples are among the hallmarks of human intelligence. CAPTCHAs (Completely Automated Public Turing test to tell Computers and Humans Apart), images used by websites to block automated interactions, are examples of problems that are easy for people but difficult for computers. CAPTCHAs add clutter and crowd letters together to create a chicken-and-egg problem for algorithmic classifiers--the classifiers work well for characters that have been segmented out, but segmenting requires an understanding of the characters, which may be rendered in a combinatorial number of ways. CAPTCHAs also demonstrate human data efficiency: A recent deep-learning approach for parsing one specific CAPTCHA style required millions of labeled examples, whereas humans solve new styles without explicit training. By drawing inspiration from systems neuroscience, we introduce recursive cortical network (RCN), a probabilistic generative model for vision in which message-passing–based inference handles recognition, segmentation, and reasoning in a unified manner.

In 2017, the Robotic Process Automation / RPA market has matured. Learning from the evolution of RPA, in this post, we explore the wider implications for Enterprise AI i.e. the deployment of Artificial Intelligence to the Enterprise The post is based on my course on Implementing Enterprise Artificial Intelligence (AI) course where we explore these ideas in detail. For this article, we consider AI to be based on Deep Learning technologies. In contrast to Machine Learning, Deep Learning implies the automatic detection of features. Features could be either a large number of possible impacting characteristics or a hierarchical set of features.

Researchers at OpenAI have launched a library of tools that can help researchers build faster, more efficient neural networks that take up less memory on GPUs. Neural networks are made up of layers of connected nodes. The architecture for these networks are highly variable depending on the data and application, but all models are limited by the way they run on GPUs. One way to train larger models for less computation is to introduce sparse matrices. A matrix is considered sparse if it is filled with mostly zeroes.

An artificial intelligence program has become the world's best chess player in just a few hours - and it did it with almost no intervention from humans. AlphaGo Zero, developed by Google subsidiary DeepMind, is a descendant of AlphaGo - the AI program that conquered the human champion of the Chinese board game Go in 2016. After four hours of training, it took on the current world champion chess-playing program, Stockfish 8. Out of 100 games, it won 28 and drew the remaining 72. Even more impressively, it achieved this feat almost completely autonomously. The AI was given a few basic rules, such as how the different chess pieces move, but was programmed with no other strategies or tactics.

The ultimate aim of AI is to produce more efficient and accurate predictions. The current trend in AI practice is to build deep learning models with TensorFlow or Keras. I have especially seen a lot of interest and research around predicting time series with Long Short-Term Memory neural network models (LSTM), which is a subtype of deep learning. I specialize in the analysis of time series data (a series of observations over time). I am particularly experienced in the utilities sector.

You'll start with an introduction to Spark and its ecosystem, and then dive into patterns that apply common techniques--including classification, clustering, collaborative filtering, and anomaly detection--to fields such as genomics, security, and finance. If you have an entry-level understanding of machine learning and statistics, and you program in Java, Python, or Scala, you'll find the book's patterns useful for working on your own data applications."

Aurora has been at the forefront of deploying computer vision, machine learning and pattern recognition solutions for over 15 years; its solutions for authentication of individuals have been installed worldwide. In fact, it is Aurora technology that enables many automated passenger validation systems at some of the world's largest airports. Underpinning our world leading accuracy are AI solutions developed through our proprietary Deep Learning technology. Our team of PhDs, world-class experts in the field, can work closely with your team to analyse requirements and tailor your solution. Our extensive experience in deploying application software in the most challenging of real world environments, means you will have a complete solution, simple to install, easy to use and fully supported.

Stochastic image reconstruction is a key part of modern digital rock physics and materials analysis that aims to create numerous representative samples of material micro-structures for upscaling, numerical computation of effective properties and uncertainty quantification. We present a method of three-dimensional stochastic image reconstruction based on generative adversarial neural networks (GANs). GANs represent a framework of unsupervised learning methods that require no a priori inference of the probability distribution associated with the training data. Using a fully convolutional neural network allows fast sampling of large volumetric images.We apply a GAN based workflow of network training and image generation to an oolitic Ketton limestone micro-CT dataset. Minkowski functionals, effective permeability as well as velocity distributions of simulated flow within the acquired images are compared with the synthetic reconstructions generated by the deep neural network. While our results show that GANs allow a fast and accurate reconstruction of the evaluated image dataset, we address a number of open questions and challenges involved in the evaluation of generative network-based methods.

This paper is concerned with paraphrase detection. The ability to detect similar sentences written in natural language is crucial for several applications, such as text mining, text summarization, plagiarism detection, authorship authentication and question answering. Given two sentences, the objective is to detect whether they are semantically identical. An important insight from this work is that existing paraphrase systems perform well when applied on clean texts, but they do not necessarily deliver good performance against noisy texts. Challenges with paraphrase detection on user generated short texts, such as Twitter, include language irregularity and noise. To cope with these challenges, we propose a novel deep neural network-based approach that relies on coarse-grained sentence modeling using a convolutional neural network and a long short-term memory model, combined with a specific fine-grained word-level similarity matching model. Our experimental results show that the proposed approach outperforms existing state-of-the-art approaches on user-generated noisy social media data, such as Twitter texts, and achieves highly competitive performance on a cleaner corpus. Keywords: 1. Introduction Paraphrase detection, Sentence Similarity, Deep learning, LSTM, CNN Twitter has for some time been a popular means for expressing opinions about a variety of subjects. Recently, the paraphrase detection task has gained significant interest in applied NLP because of the need to deal with the pervasive problem of linguistic variation. Paraphrase detection is an NLP classification problem. Given a pair of sentences, the system determines the semantic similarity between the two sentences.

Artificial intelligence (AI) is intrinsically data-driven. It calls for the application of statistical concepts through human-machine collaboration during generation of data, development of algorithms, and evaluation of results. This paper discusses how such human-machine collaboration can be approached through the statistical concepts of population, question of interest, representativeness of training data, and scrutiny of results (PQRS). The PQRS workflow provides a conceptual framework for integrating statistical ideas with human input into AI products and research. These ideas include experimental design principles of randomization and local control as well as the principle of stability to gain reproducibility and interpretability of algorithms and data results. We discuss the use of these principles in the contexts of self-driving cars, automated medical diagnoses, and examples from the authors' collaborative research.