This class provides a practical introduction to deep learning, including theoretical motivations and how to implement it in practice. As part of the course we will cover multilayer perceptrons, backpropagation, automatic differentiation, and stochastic gradient descent. Moreover, we introduce convolutional networks for image processing, starting from the simple LeNet to more recent architectures such as ResNet for highly accurate models. Secondly, we discuss sequence models and recurrent networks, such as LSTMs, GRU, and the attention mechanism. Throughout the course we emphasize efficient implementation, optimization and scalability, e.g. to multiple GPUs and to multiple machines. The goal of the course is to provide both a good understanding and good ability to build modern nonparametric estimators.

A self-driving car approaches a stop sign, but instead of slowing down, it accelerates into the busy intersection. An accident report later reveals that four small rectangles had been stuck to the face of the sign. These fooled the car's onboard artificial intelligence (AI) into misreading the word'stop' as'speed limit 45'. Such an event hasn't actually happened, but the potential for sabotaging AI is very real. Researchers have already demonstrated how to fool an AI system into misreading a stop sign, by carefully positioning stickers on it1. They have deceived facial-recognition systems by sticking a printed pattern on glasses or hats. And they have tricked speech-recognition systems into hearing phantom phrases by inserting patterns of white noise in the audio.

A mesothelioma prognostic model from medical machine learning firm Owkin has been showcased in the journal Nature, and is being used to help further drug research into the often fatal disease. The paper, entitled "Deep learning-based classification of mesothelioma improves prediction of patient outcomes" describes Owkin's technology called MesoNet, which has been trained using images from nearly 3,000 mesothelioma patients. Owkin used data from MESOBANK, a dataset containing images from several French institutions, and results were validated by experts in pathology at the renowned French Cancer Institute, Centre Leon Berard. As well as giving a prognosis, Owkin was able to use its deep learning technology to highlight regions of interest in the image associated with prognosis prediction. This has led to identification that helps explain different subtypes of the disease, the company said.

In the previous blog, we talked about how the Autoencoders in Keras can help us innovate and solve problems that do not appear solvable even after increasing hidden layers and training time. In that blog, we learned that different model architectures conjured through different insights can help us solve a problem statement elegantly and with much less complexity than blindly stacking up layer after layer. We saw this with a Computer Vision research example which was an Automated De-Blurring problem. Starting with a vanilla Convolutional Neural Network, we ended up witnessing how being smart, innovative and using our insights and instincts, we could solve what seemed like an unsolvable problem which was made possible by the flexibility of the Functional API in Keras. We called adding layers and increasing training time as the'go to' thing to do.

Deep learning is a sub-field of machine learning that is rapidly rising and is driving a lot of developments that has already transformed traditional internet businesses like web search and advertising. In the past couple of years, deep learning has gotten good from reading X-ray images, to delivering personalized education, precision agriculture, and even to self-driving cars. Over the next decades, we will have an opportunity to build an amazing world and society that is AI powered, and maybe you will play a big role in the creation of this AI powered society. What exactly is AI? AI is the new electricity. About 100 years ago, the electrification of our society has transformed every major industry like, transportation, manufacturing, healthcare, communication and many more.

Just the mention of AI and the brain invokes pictures of Terminator machines destroying the world. Thankfully, the present picture is significantly more positive. So, let's explore how AI is helping our planet and at last benefiting humankind. In this blog on Artificial Intelligence applications, I'll be discussing how AI has impacted various fields like healthcare, finance, agriculture, and so on. Marketing is a way to sugar coat your products to attract more customers.

How has the landscape changed for the leading deep learning frameworks in the past six months? To answer that question, I looked at the number of job listings on Indeed, Monster, LinkedIn, and SimplyHired. I also evaluated changes in Google search volume, GitHub activity, Medium articles, ArXiv articles, and Quora topic followers. Overall, these sources paint a comprehensive picture of growth in demand, usage, and interest. We've recently seen several important developments in the TensorFlow and PyTorch frameworks.

Professor Jackie Hunter looks at why the pharmaceutical industry has been so slow to adopt artificial intelligence-based technologies and makes a prediction for the industry's future, including a significantly increased amount of interplay between large technology and pharma companies. There is no doubt that the pharmaceutical industry is ripe for disruption. Costs over the past two decades have soared – it currently costs USD 2.6bn to develop a drug – but the industry has not delivered high levels of innovation in return. True, important new medicines have been delivered, especially in biological areas such as immune-oncology and multiple sclerosis, but other areas such as dementia and brain cancer have not seen therapeutic advances. The past two decades have also seen an explosion of biomedical data, making it impossible for even the most learned researchers to process and garner real insight from this wealth of information.

A GPU is one of the most important components of modern-day artificial intelligence and deep learning architecture. Enterprises and developers are constantly on the lookout for tools that help them build and manage end-to-end data science and analytics pipelines seamlessly. RAPIDS is one such a tool incubated by NVIDIA based on the company's expert experience in hardware and data science. RAPIDS uses NVIDIA CUDA primitives for low-level compute optimisation, and lets developers use GPU parallelism and high-bandwidth memory speed through user-friendly Python interfaces. RAPIDS's also helps with data preparation tasks for data science pipelines.

Researchers have successfully shrunk a giant language model to use in commercial applications. In October of last year, for example, Google released a model called BERT that passed a long-held reading-comprehension benchmark in the field. The larger version of the model had 340 million data parameters, and training it just one time through cost enough electricity to power a US household for 50 days. Four months later, OpenAI quickly topped it with its model GPT-2. The model demonstrated an impressive knack for constructing convincing prose; it also used 1.5 billion parameters. Now, MegatronLM, the latest and largest model from Nvidia, has 8.3 billion parameters.