This article proposes an active learning method for high dimensional data, based on intrinsic data geometries learned through diffusion processes on graphs. Diffusion distances are used to parametrize low-dimensional structures on the dataset, which allow for high-accuracy labelings of the dataset with only a small number of carefully chosen labels. The geometric structure of the data suggests regions that have homogeneous labels, as well as regions with high label complexity that should be queried for labels. The proposed method enjoys theoretical performance guarantees on a general geometric data model, in which clusters corresponding to semantically meaningful classes are permitted to have nonlinear geometries, high ambient dimensionality, and suffer from significant noise and outlier corruption. The proposed algorithm is implemented in a manner that is quasilinear in the number of unlabeled data points, and exhibits competitive empirical performance on synthetic datasets and real hyperspectral remote sensing images.

Deep (neural) networks have been applied productively in a wide range of supervised and unsupervised learning tasks. Unlike classical machine learning algorithms, deep networks typically operate in the overparameterized regime, where the number of parameters is larger than the number of training data points. Consequently, understanding the generalization properties and role of (explicit or implicit) regularization in these networks is of great importance. Inspired by the seminal work of Donoho and Grimes in manifold learning, we develop a new measure for the complexity of the function generated by a deep network based on the integral of the norm of the tangent Hessian. This complexity measure can be used to quantify the irregularity of the function a deep network fits to training data or as a regularization penalty for deep network learning. Indeed, we show that the oft-used heuristic of data augmentation imposes an implicit Hessian regularization during learning. We demonstrate the utility of our new complexity measure through a range of learning experiments.

Quantifying and measuring uncertainty in deep neural networks, despite recent important advances, is still an open problem. Bayesian neural networks are a powerful solution, where the prior over network weights is a design choice, often a normal distribution or other distribution encouraging sparsity. However, this prior is agnostic to the generative process of the input data, which might lead to unwarranted generalization for out-of-distribution tested data. We suggest treating the generative process of the input data as a confounder for the relation between the input and the discriminative function, thereby conditioning the prior of the network weights on the distribution of the input. We propose an algorithm for modeling this confounder through neural connectivity patterns. This approach is ultimately translated into a new deep architecture---a compact hierarchy of networks. We demonstrate that sampling networks from this hierarchy, proportionally to their posterior, is efficient and enables estimating various types of uncertainties. Empirical evaluations of our method demonstrate significant improvement compared to state-of-the-art calibration and out-of-distribution detection methods.

In this paper, we develop a neural summarization model which can effectively process multiple input documents and distill Transformer architecture with the ability to encode documents in a hierarchical manner. We represent cross-document relationships via an attention mechanism which allows to share information as opposed to simply concatenating text spans and processing them as a flat sequence. Our model learns latent dependencies among textual units, but can also take advantage of explicit graph representations focusing on similarity or discourse relations. Empirical results on the WikiSum dataset demonstrate that the proposed architecture brings substantial improvements over several strong baselines.

Amazon has a long and rich heritage of Machine learning and Deep Learning Solutions such as personalized shopping recommendations, automated fulfillment and inventory management, robotic drones for fast delivery, a checkout-free computer vision retail experience with Amazon Go, voice interactions with Alexa and a lot more. And now, AWS is the center of gravity for Artificial Intelligence/Machine Learning because of the massive volume of data stored and processed on our Big Data platform. By lowering the barriers for AI/ML workloads with an innovative suite of products and services, AWS enables you to easily build machine learning powered smart applications to meet complex business needs. We will kick-off this workshop with an overview of the AWS AI/ML platform, demonstrating the ease of use and the art of the possible for solving a real-world scenario, followed by an AI/ML case study. We will then have two tracks with multiple hands-on sessions for building your own smart applications using AWS AI driven services such as Amazon Lex, Amazon Polly, Amazon Rekognition, as well as Amazon SageMaker, an end to end ML platform that accelerates the process of building, training, and deploying machine learning models at any scale.

It is always attributed to emerging something interesting, when cloud computing, geo-mapping, and machine learning conjoin. Google has been using this updated technology, AI with satellite data, throttling illegal fishing. Adding to it, the technology creates 22 million data a day that addresses the ship's location on any water body. Creating Global Fishing Watch, made things a lot easier, they could now find the position where the fishing is going on or could identify the purpose of the vessel at sea. Artificial Intelligence and machine learning together is a phenomenally in usage through backend in our daily lives.

Me: Alexa please remind me my morning yoga sculpt class is at 5:30am. Alexa: I have added Tequila to your shopping list. We talk to our devices, and sometimes they recognize what we are saying correctly. We use free services to translate foreign language phrases encountered online into English, and sometimes they give us an accurate translation. Although natural language processing has been improving by leaps and bounds, it still has considerable room for improvement.

"Deep learning is neither deep, nor is it learning," says Babak Hodjat, the vice president of projects for "Evolutionary AI" at IT services giant Cognizant Technologies. Hodjat's critique is part of a fascinating exploration of AI taking shape at IT services firm Cognizant Technology Solutions, a twenty-five-year-old company based in Teaneck, New Jersey that last year made nearly $16 billion in revenue serving some of the biggest companies in the world. For years, this IT giant has talked about "digital transformation," something that is large and significant but also something hard to get one's mind around because it very often seems vague and undefined. And then in December, Cognizant gave a whole new grounding and precision to that digital work by acquiring certain assets from an eleven-year-old AI startup Sentient Technologies. The company, co-founded by Hodjat, has been pursuing a thrilling line of work in what's called "evolutionary computation," where many algorithms, including conventional artificial neural networks, can be tested in parallel for "fitness," to select an optimal network to perform a task.

The simplest way to discuss about AI is by considering the perspective of humans. We know that humans are the most intellectual creatures in this world. So, it is better to compare Artificial Intelligence with Human Intelligence to get a clear vision of AI. AI, a wide branch of Computer Science, is used to create intelligent machines that can recognize human speech, detect objects, solve problems and learn like humans. Humans can write and read text-data in any language.

There are a few different ways to build IKEA furniture. Each will, ideally, lead to a completed couch or chair. But depending on the details, one approach will make more sense than the others. Getting the hang of it? Toss the manual aside and go solo.