GPflow is a package for building Gaussian process models in Python. It implements modern Gaussian process inference for composable kernels and likelihoods. GPflow builds on TensorFlow 2.4 and TensorFlow Probability for running computations, which allows fast execution on GPUs. The online documentation (latest release)/(develop) contains more details. It was originally created by James Hensman and Alexander G. de G. Matthews.

Deep learning models are wonderful, and we always want to use the newest cutting edge solutions to get the best results. But once in a while you stumble upon a relevant whitepaper that looks relevant to the task on hands, even though it's made a few years ago. And few years is an ethernity for the deep learning projects: old versions of frameworks, CUDA, python, etc -- nothing of that is easy to just install and laucnh on the modern systems. Usual answer for that would be Anaconda, but it doesn't provide enough isolation when it comes to the GPU accelerated models. My way of dealing with this problem would be of no surprise to the most: containerisation, in other words -- Docker.

Generative Adversarial Networks (GANs) are one of the hottest topics in computer science in recent times. They are a clever way of training a generative model (unsupervised learning) by framing the problem as a supervised learning problem. The main idea is that two different models are trained simultaneously by an adversarial process. Generative adversarial networks are based on a game theoretic scenario in which the generator network must compete against an adversary. The generator network directly produces samples.

Deep learning is changing our lives in small and large ways every day. Whether it's Siri or Alexa following our voice commands, the real-time translation apps on our phones, or the computer vision technology enabling smart tractors, warehouse robots, and self-driving cars, every month seems to bring new advances. And almost all of these deep learning applications are written in one of three frameworks: TensorFlow, PyTorch, and JAX. Which of these deep learning frameworks should you use? In this article, we'll take a high-level comparative look at TensorFlow, PyTorch, and JAX. We'll aim to give you some idea of the types of applications that play to their strengths, as well as consider factors like community support and ease-of-use.

StyleGAN is one of the most popular generative models by NVIDIA. First released by NVIDIA in 2018, StyleGAN is one of the most well-known image generation GANs. For best results, StyleGAN needs to be trained on tens of thousands of images and requires powerful GPU resources. In 2020, NVIDIA released StyleGAN2 ADA with a feature that enables new models to be cross-trained from another. By starting with an existing high-quality model and resuming training with a different set of images, it's possible to get good results with a few thousand images and a lot less computing power.

The case study is based on Kaggle RSNA Pneumonia detection challenge which was done on In this Kaggle challenge we need to detect a visual signal for pneumonia in medical images. The solution should be able to automatically locate lung opacities on chest radiographs. In US it accounts for 500K emergency visits to emergency departments. Accurately diagnosing pneumonia is tedious work. Trained radiologist requires various tests, examinations and chest radiograph (CXR)to diagnose the disease.

AbbVie is a research-based biopharmaceutical company that serves more than 30 million patients in 175 countries. With its global scale, AbbVie partnered with Intel to optimize processes for its more than 47,000 employees. This whitepaper highlights two use cases that are important to AbbVie's research. The first is Abbelfish Machine Translation, AbbVie's language translation service based on the Transformer NLP model, that leverages second-generation Intel Xeon Scalable processors and the Intel Optimization for TensorFlow with Intel oneAPI Deep Neural Network Library (oneDNN). AbbVie was able to achieve a 1.9x improvement in throughput for Abbelfish language translation using Intel Optimization for TensorFlow 1.15 with oneAPI Deep Neural Network Library when compared to TensorFlow 1.15 without oneDNN.1

Mask R-CNN is an object detection model based on deep convolutional neural networks (CNN) developed by a group of Facebook AI researchers in 2017. The model can return both the bounding box and a mask for each detected object in an image. The model was originally developed in Python using the Caffe2 deep learning library. The original source code is available on GitHub. To support the Mask R-CNN model in more libraries that are currently more popular, such as TensorFlow, there is a popular popular open-source project called that offers an implementation based on Keras and TensorFlow 1.3. Google officially released TensorFlow 2.0 in September 2020. TensorFlow 2.0 is better organized and much easier to learn compared to TensorFlow 1.0.

The complexity of artificial intelligence (AI) machine learning requires specialized knowledge and experience. Microsoft hopes to change that. Today Microsoft provided a general preview of Lobe, a software application available at no charge that enables anyone to build machine learning models--no technical skills required. Recent trends such as decentralized cloud computing, adaptation of GPU for general computing, increasing availability of big data sets, and advances in deep learning, a subset of AI machine learning, has spurred a modern-day AI gold rush. Global investment in AI in just half a decade has soared across sectors and geographies.

Recurrent networks like LSTM and GRU are powerful sequence models. I will explain how to create recurrent networks in TensorFlow and use them for sequence classification and labelling tasks. If you are not familiar with recurrent networks, I suggest you take a look at Christopher Olah's great article first. On the TensorFlow part, I also expect some basic knowledge. The official tutorials are a good place to start.