These days, nearly all the artificial intelligence-based products in our lives rely on "deep neural networks" that automatically learn to process labeled data. For most organizations and individuals, though, deep learning is tough to break into. To learn well, neural networks normally have to be quite large and need massive datasets. This training process usually requires multiple days of training and expensive graphics processing units (GPUs) -- and sometimes even custom-designed hardware. But what if they don't actually have to be all that big, after all?

This post is part of the series in which we are going to cover the following topics. In the previous blog we discussed about PyTorch, it's strengths and why should you learn it. We also had a brief look at Tensors – the core data structure in PyTorch. In this blog, we will jump into some hands-on examples of using pre-trained networks present in TorchVision module for Image Classification. Torchvision package consists of popular datasets, model architectures, and common image transformations for computer vision.

The world is changing and so is the technology serving it. It's crucial for everyone to keep up with the rapid changes in technology. One of the domains which is witnessing the fastest and largest evolution is Artificial Intelligence. We are training our machines to learn and the results are now getting better and better. There are GANs which can generate new images, Deep Learning models for translating signed language into text, and what not!

The convergence of three emergent technologies: Intelligent Learning Systems (AI, ML), Quantum Computing (QC) and Distributed Ledgers (DLT) will likely have a transforming impact on our society and shape the future of Information Technology. What will be the direction of future AI, ML technology initiatives in the financial industry, in a broad spectrum of research, development & commercialisation efforts for ML, AI and DLT in the quantum domain? As an example, quantum computing is finding a vital application in providing speed-ups in ML, critical in our "big data" world. This will have a profound impact on Investment Portfolio Management, High Frequency Trading, Loan Origination and processing, Fraud Detection, Risk Modelling and calculating credit ratings. Future use cases that can leverage these three technologies include a secure and transparent distributed personal financial data (PII) marketplace, and a secondary mortgage platform with a tokenised exchange combining DLT, post-QC cryptographic algorithms and deep learning technologies.

Simultaneous localization and mapping (SLAM) is the computational problem of constructing or updating a map of an unknown environment while simultaneously keeping track of a robot's location within it. SLAM is being gradually developed towards Spatial AI, the common sense spatial reasoning that will enable robots and other artificial devices to operate in general ways in their environments. This will enable robots to not just localize and build geometric maps, but actually interact intelligently with scenes and objects. A key technology that is helping this progress is deep learning, which has enabled many recent breakthroughs in computer vision and other areas of AI. In the context of Spatial AI, deep learning has most obviously had a big impact on bringing semantic meaning to geometric maps of the world.

Deep-learning techniques have made it easier and easier for anyone to forge convincing misinformation. Two researchers at the United Nations decided to find out. In a new paper, they used only open-source tools and data to show how quickly they could get a fake UN speech generator up and running. They used a readily available language model that had been trained on text from Wikipedia and fine-tuned it on all the speeches given by political leaders at the UN General Assembly from 1970 to 2015. Thirteen hours and $7.80 later (spent on cloud computing resources), their model was spitting out realistic speeches on a wide variety of sensitive and high-stakes topics from nuclear disarmament to refugees.

Artificial intelligence seems to be everywhere these days. The news has stories about poetry-writing AI, the experts consider AI "the new electricity" and even AI whiskey is going to make an appearance soon. When you try reading these articles, there's usually a flood of information coming at you. But what do these concepts even mean? With this series of blog posts, we're going to address all the questions you've ever had about this topic and take you on an amazing adventure. In this first part, we're going to introduce the concepts of machine learning, neural networks, and deep learning. You don't need any previous knowledge about these topics to follow this article, so settle in and keep reading! Let's start with a basic concept: functions.

Watch a quick demonstration of how to use MATLAB, a simple webcam, and a deep neural network to identify objects in your surroundings. This demo uses AlexNet, a pretrained deep convolutional neural network (CNN or ConvNet) that has been trained on over a million images. The example has two parts: setting up the camera and performing object recognition. The first part shows how to use the webcam command to acquire images from the camera. Using the drawnow command, MATLAB is able to continuously update and display images taken by the camera.

We are excited to announce that, to help us get there, we have acquired Fabula AI (Fabula), a London-based start-up, with a world-class team of machine learning researchers who employ graph deep learning to detect network manipulation. Graph deep learning is a novel method for applying powerful ML techniques to network-structured data. The result is the ability to analyze very large and complex datasets describing relations and interactions, and to extract signals in ways that traditional ML techniques are not capable of doing. Twitter has been criticized for the amount of fake news and misinformation that easily spreads on its platform. Though the company has taken steps to combat such misinformation in recent years, fake news is still a major problem for the social network.

The timeliness of detection of a sepsis event in progress is a crucial factor in the outcome for the patient. Machine learning models built from data in electronic health records can be used as an effective tool for improving this timeliness, but so far the potential for clinical implementations has been largely limited to studies in intensive care units. This study will employ a richer data set that will expand the applicability of these models beyond intensive care units. Furthermore, we will circumvent several important limitations that have been found in the literature: 1) Models are evaluated shortly before sepsis onset without considering interventions already initiated. 2) Machine learning models are built on a restricted set of clinical parameters, which are not necessarily measured in all departments. 3) Model performance is limited by current knowledge of sepsis, as feature interactions and time dependencies are hardcoded into the model. In this study, we present a model to overcome these shortcomings using a deep learning approach on a diverse multicenter data set. We used retrospective data from multiple Danish hospitals over a seven-year period. Our sepsis detection system is constructed as a combination of a convolutional neural network and a long short-term memory network. We suggest a retrospective assessment of interventions by looking at intravenous antibiotics and blood cultures preceding the prediction time. Results show performance ranging from AUROC 0.856 (3 hours before sepsis onset) to AUROC 0.756 (24 hours before sepsis onset). We present a deep learning system for early detection of sepsis that is able to learn characteristics of the key factors and interactions from the raw event sequence data itself, without relying on a labor-intensive feature extraction work.