I hope this review helps the readers to choose the right book for their learning needs. This book is written by the creator of Keras -- Francois Chollet. He is also Google AI Researcher. The book is divided into 2 parts of total 9 chapters. First part is devoted to explain the building blocks of machine learning, deep learning and Keras framework.

Researchers are developing artificial intelligence that could assess climate change tipping points. The deep-learning algorithm could act as an early warning system against runaway climate change. In a new paper, the researchers look at thresholds beyond which rapid or irreversible change happens in a system. "We found that the new algorithm was able to not only predict the tipping points more accurately than existing approaches but also provide information about what type of state lies beyond the tipping point," said Chris Bauch, a professor of applied mathematics at the University of Waterloo. "Many of these tipping points are undesirable, and we'd like to prevent them if we can." Some tipping points that are often associated with runaway climate change include melting Arctic permafrost, which could release vast amounts of methane and spur further rapid heating; breakdown of oceanic current systems, which could lead to almost immediate changes in weather patterns; or ice sheet disintegration, which could lead to rapid sea-level change.

A new learned legged locomotion study uses massive parallelism on a single GPU to get robots up and walking on flat terrain in under four minutes, and on uneven terrain in twenty minutes. Although deep reinforcement learning (DRL) has achieved impressive results in robotics, the amount of data required to train a policy increases dramatically with task complexity. One way to improve the quality and time-to-deployment of DRL policies is to use massive parallelism. In the paper Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learning, a research team from ETH Zurich and NVIDIA proposes a training framework that enables fast policy generation for real-world robotic tasks using massive parallelism on a single workstation GPU. Compared to previous methods, the approach can reduce training time by multiple orders of magnitude.

This will enable users of MVTec software products to benefit from AI accelerator hardware that is compatible with the OpenVINO toolkit from Intel. As a result, significantly faster deep learning inference times can be achieved on Intel processors including CPUs, GPUs and VPUs for key workloads. By expanding the range of supported hardware, users can now harness the performance of a wide range of Intel devices to accelerate their deep learning applications and are no longer limited to a few specific devices. At the same time, the integration works seamlessly and is not bound to certain hardware specifics. Simply by changing parameters, the inference of an existing deep learning application can now be executed on devices supported by the OpenVINO toolkit.

This article is a write-up on how I built Text2Art.com in a week. Text2Art is an AI-powered art generator based on VQGAN CLIP that can generate all kinds of art such as pixel art, drawing, and painting from just text input. The article follows my thought process from experimenting with VQGAN CLIP, building a simple UI with Gradio, switching to FastAPI to serve the models, and finally to using Firebase as a queue system. Feel free to skip to the parts that you are interested in. If you like the project, you can vote for the project here.

Why would you need a robot with a ten-inch screen, camera, sensors, and a bunch of other gadgets to go around your home and make Wall-E noises? Because Amazon thinks it might be useful in the future. Astro, Amazon's latest innovation, looks a lot like an Echo Show on wheels. It packs a lot of interesting technology and shows just how far deep learning, sensor technology, and mobile robots have come. But a successful product needs a lot more than a nice-looking robot that brings together cutting-edge technologies and tried-and-tested applications.

In this course, we aim to specialize in artificial intelligence by doing Machine Learning and Deep Learning Projects at various levels. Before starting the course, you must have basic Python knowledge. Our aim in this course is to turn real-life problems that seem difficult to do into projects and then solve them using latest versions of artificial intelligence algorithms and Python(3.8). This course was prepared in July 2021. We will carry out some of our projects using machine learning and some using deep learning algorithms.

Many companies in the modern world are greatly reliant on machine learning models and monitoring tools. These tools help in animation, unsupervised learning, avoid prediction errors, self-iteration based on data, and dataset visualization. The market for these tools is expected to grow by US$4 billion. You might have plenty of data in your bag, but it is useless if you can't use it to understand your business. Anodot is an AI monitoring tool that understands your data automatically. It can monitor multiple things simultaneously, such as customer experience, partners, revenue, and Telco networking.

Graph convolutional neural networks (GCNNs) are popular deep learning architectures that, upon replacing regular convolutions with graph filters (GFs), generalize CNNs to irregular domains. However, classical GFs are prone to numerical errors since they consist of high-order polynomials. This problem is aggravated when several filters are applied in cascade, limiting the practical depth of GCNNs. To tackle this issue, we present the neighborhood graph filters (NGFs), a family of GFs that replaces the powers of the graph shift operator with $k$-hop neighborhood adjacency matrices. NGFs help to alleviate the numerical issues of traditional GFs, allow for the design of deeper GCNNs, and enhance the robustness to errors in the topology of the graph. To illustrate the advantage over traditional GFs in practical applications, we use NGFs in the design of deep neighborhood GCNNs to solve graph signal denoising and node classification problems over both synthetic and real-world data.

Recent work has raised concerns on the risk of spurious correlations and unintended biases in statistical machine learning models that threaten model robustness and fairness. In this paper, we propose a simple and intuitive regularization approach to integrate causal knowledge during model training and build a robust and fair model by emphasizing causal features and de-emphasizing spurious features. Specifically, we first manually identify causal and spurious features with principles inspired from the counterfactual framework of causal inference. Then, we propose a regularization approach to penalize causal and spurious features separately. By adjusting the strength of the penalty for each type of feature, we build a predictive model that relies more on causal features and less on non-causal features. We conduct experiments to evaluate model robustness and fairness on three datasets with multiple metrics. Empirical results show that the new models built with causal awareness significantly improve model robustness with respect to counterfactual texts and model fairness with respect to sensitive attributes.