Federated learning (FL) represents a pivotal shift in machine learning (ML) as it enables collaborative training of local ML models coordinated by a central aggregator, all without the need to exchange local data. However, its application on edge devices is hindered by limited computational capabilities and data communication challenges, compounded by the inherent complexity of Deep Learning (DL) models. Model pruning is identified as a key technique for compressing DL models on devices with limited resources. Nonetheless, conventional pruning techniques typically rely on manually crafted heuristics and demand human expertise to achieve a balance between model size, speed, and accuracy, often resulting in sub-optimal solutions. In this study, we introduce an automated federated learning approach utilizing informed pruning, called AutoFLIP, which dynamically prunes and compresses DL models within both the local clients and the global server. It leverages a federated loss exploration phase to investigate model gradient behavior across diverse datasets and losses, providing insights into parameter significance. Our experiments showcase notable enhancements in scenarios with strong non-IID data, underscoring AutoFLIP's capacity to tackle computational constraints and achieve superior global convergence.

When it comes to artificial intelligence, it is hard to keep Google away from bringing in a new array of services and products on a regular basis. In the month of January, the tech giant launched a number of products such as LaserTagger, Meena and Reformer, to name a few. Just like the previous month, Google has rolled down a number of new tools/techniques to look at, which will benefit a host of people in regard to artificial intelligence and other related streams. Here is a list of the products launched by Google in February 2020. In recent times, transfer learning has helped natural learning processing (NLP) reach new heights, which happened due to the pre-training of models on the unlimited availability of unlabeled text data.

Video filmed and edited for TV is typically created and viewed in landscape, but problematically, aspect ratios like 16:9 and 4:3 don't always fit the display being used for viewing. Fortunately, Google is on the case. Given a video and a target dimension, it analyzes the video content and develops optimal tracking and cropping strategies, after which it produces an output video with the same duration in the desired aspect ratio. As Google Research senior software engineer Nathan Frey and senior software engineer Zheng Sun note in a blog post, traditional approaches for reframing video usually involve static cropping, which often leads to unsatisfactory results. More bespoke approaches are superior, but they typically require video curators to manually identify salient content in each frame, track their transitions from frame to frame, and adjust crop regions accordingly throughout the video.

How many times have you seen a video being badly cropped when you watch it on a mobile device? It's quite frustrating and annoying, and most of the time, there's not much you can do about it. To address this problem, Google's AI team has developed an open-source solution, Autoflip, that reframes the video that suits the target device or dimension (landscape, square, portrait, etc.). Autoflip works in three stages: Shot (scene) detection, video content analysis, and reframing. The first part is scene detection, in which the machine learning model needs to detect the point before a cut or a jump from one scene to another. So it compares one frame with the previous one before to detect the change of colors and elements.