Many people in the tech world now have a solid understanding of AI. Others are just getting started and asking questions like: What are the differences between deep learning and machine learning? How are they different, and how can they benefit organizations? Enterprises and their leaders who are looking to get started should first get familiar with the fundamentals of deep learning and the corresponding terminology, as well as understand the current challenges to AI adoption and how to address them. In this article, I'll aim to provide a definitive overview of the topic, along with links to several resources that you may find useful.

The brilliant minds at Google's sister-company Deepmind are at it again. This time it appears they've developed a system by which driverless cars can navigate the same way humans do: by following directions. A long time ago, before the millenials were born, people had to drive in their cars without any form of GPS navigation. If you wanted to go some place new you used a paper map – they were like offline screenshots of a Google Maps image. Or someone gave you a list of directions.

Complete hands-on machine learning tutorial with data science, Tensorflow, artificial intelligence, and neural networks Machine Learning and artificial intelligence (AI) is everywhere; if you want to know how companies like Google, Amazon, and even Udemy extract meaning and insights from massive data sets, this data science course will give you the fundamentals you need. Data Scientists enjoy one of the top-paying jobs, with an average salary of $120,000 according to Glassdoor and Indeed. If you've got some programming or scripting experience, this course will teach you the techniques used by real data scientists and machine learning practitioners in the tech industry - and prepare you for a move into this hot career path. This comprehensive machine learning tutorial includes over 80 lectures spanning 12 hours of video, and most topics include hands-on Python code examples you can use for reference and for practice. I'll draw on my 9 years of experience at Amazon and IMDb to guide you through what matters, and what doesn't.

Deep learning is one of the most compelling new technologies available to businesses and is poised to be a game changer for many. Now is an ideal time for companies to consider leveraging deep learning because it is quickly moving from the realm of academic research to one in which new B2B software platforms can leverage the technology effectively. Gartner recently reported that the use of artificial intelligence (of which deep learning is a specific category) among enterprises tripled in the past year, with 37 percent of organizations reporting that they use it. It's a specific type of machine learning in which software algorithms ingest large amounts of data and then extract insights from patterns within it. That data can be customer behavior, images, sound files, video, maps, sales figures -- provided the data is structured appropriately; the possibilities are endless.

The buildup of abnormal tau proteins in the brain in neurofibrillary tangles is a feature of Alzheimer's disease, but it also accumulates in other neurodegenerative diseases, such as chronic traumatic encephalopathy and additional age-related conditions. Accurate diagnosis of neurodegenerative diseases is challenging and requires a highly-trained specialist. Researchers at the Center for Computational and Systems Pathology at Mount Sinai developed and used the Precise Informatics Platform to apply powerful machine learning approaches to digitized microscopic slides prepared using tissue samples from patients with a spectrum of neurodegenerative diseases. Applying deep learning, these images were used to create a convolutional neural network capable of identifying neurofibrillary tangles with a high degree of accuracy directly from digitized images. "Utilizing artificial intelligence has great potential to improve our ability to detect and quantify neurodegenerative diseases, representing a major advance over existing labor-intensive and poorly reproducible approaches," said lead investigator John Crary, MD, PhD, Professor of Pathology and Neuroscience at the Icahn School of Medicine at Mount Sinai.

Graph processes model a number of important problems such as identifying the epicenter of an earthquake or predicting weather. In this paper, we propose a Graph Convolutional Recurrent Neural Network (GCRNN) architecture specifically tailored to deal with these problems. GCRNNs use convolutional filter banks to keep the number of trainable parameters independent of the size of the graph and of the time sequences considered. We also put forward Gated GCRNNs, a time-gated variation of GCRNNs akin to LSTMs. When compared with GNNs and another graph recurrent architecture in experiments using both synthetic and real-word data, GCRNNs significantly improve performance while using considerably less parameters.

In this paper we address the problem of artist style transfer where the painting style of a given artist is applied on a real world photograph. We train our neural networks in adversarial setting via recently introduced quadratic potential divergence for stable learning process. To further improve the quality of generated artist stylized images we also integrate some of the recently introduced deep learning techniques in our method. To our best knowledge this is the first attempt towards artist style transfer via quadratic potential divergence. We provide some stylized image samples in the supplementary material. The source code for experimentation was written in PyTorch and is available online in my GitHub repository.

We introduce a probabilistic robustness measure for Bayesian Neural Networks (BNNs), defined as the probability that, given a test point, there exists a point within a bounded set such that the BNN prediction differs between the two. Such a measure can be used, for instance, to quantify the probability of the existence of adversarial examples. Building on statistical verification techniques for probabilistic models, we develop a framework that allows us to estimate probabilistic robustness for a BNN with statistical guarantees, i.e., with a priori error and confidence bounds. We provide experimental comparison for several approximate BNN inference techniques on image classification tasks associated to MNIST and a two-class subset of the GTSRB dataset. Our results enable quantification of uncertainty of BNN predictions in adversarial settings.

The field of few-shot learning has been laboriously explored in the supervised setting, where per-class labels are available. On the other hand, the unsupervised few-shot learning setting, where no labels of any kind are required, has seen little investigation. We propose a method, named Assume, Augment and Learn or AAL, for generating few-shot tasks using unlabeled data. We randomly label a random subset of images from an unlabeled dataset to generate a support set. Then by applying data augmentation on the support set's images, and reusing the support set's labels, we obtain a target set. The resulting few-shot tasks can be used to train any standard meta-learning framework. Once trained, such a model, can be directly applied on small real-labeled datasets without any changes or fine-tuning required. In our experiments, the learned models achieve good generalization performance in a variety of established few-shot learning tasks on Omniglot and Mini-Imagenet.

Novelty detection is the unsupervised problem of identifying anomalies in test data which significantly differ from the training set. Novelty detection is one of the classic challenges in Machine Learning and a core component of several research areas such as fraud detection, intrusion detection, medical diagnosis, data cleaning, and fault prevention. While numerous algorithms were designed to address this problem, most methods are only suitable to model continuous numerical data. Tackling datasets composed of mixed-type features, such as numerical and categorical data, or temporal datasets describing discrete event sequences is a challenging task. In addition to the supported data types, the key criteria for efficient novelty detection methods are the ability to accurately dissociate novelties from nominal samples, the interpretability, the scalability and the robustness to anomalies located in the training data. In this thesis, we investigate novel ways to tackle these issues. In particular, we propose (i) an experimental comparison of novelty detection methods for mixed-type data (ii) an experimental comparison of novelty detection methods for sequence data, (iii) a probabilistic nonparametric novelty detection method for mixed-type data based on Dirichlet process mixtures and exponential-family distributions and (iv) an autoencoder-based novelty detection model with encoder/decoder modelled as deep Gaussian processes.