Federated Learning (FL) is a promising research paradigm that enables the collaborative training of machine learning models among various parties without the need for sensitive information exchange. Nonetheless, retaining data in individual clients introduces fundamental challenges to achieving performance on par with centrally trained models. Our study provides an extensive review of federated learning applied to visual recognition. It underscores the critical role of thoughtful architectural design choices in achieving optimal performance, a factor often neglected in the FL literature. Many existing FL solutions are tested on shallow or simple networks, which may not accurately reflect real-world applications.

Federated Learning (FL) is a promising research paradigm that enables the collaborative training of machine learning models among various parties without the need for sensitive information exchange. Nonetheless, retaining data in individual clients introduces fundamental challenges to achieving performance on par with centrally trained models. Our study provides an extensive review of federated learning applied to visual recognition. It underscores the critical role of thoughtful architectural design choices in achieving optimal performance, a factor often neglected in the FL literature. Many existing FL solutions are tested on shallow or simple networks, which may not accurately reflect real-world applications.

I recently started an AI-focused educational newsletter, that already has over 70,000 subscribers. TheSequence is a no-BS (meaning no hype, no news etc) ML-oriented newsletter that takes 5 minutes to read. The goal is to keep you up to date with machine learning projects, research papers and concepts. An image is worth a thousand words says the old wisdom quote that captures the importance of visual analysis in the learning process of human species. Every time we are presented with a visual scene, our brains make thousands of inferences about the objects in it and their contextual nature.

When a hardware-related system disruption like an outage due to hard drive failure happens, the path to recovery includes checking hardware support information, describing the problem to a support representative, waiting for a field technician to arrive, hoping the technician can resolve the issue in a timely manner. Our team of researchers recently published paper "Fine-Grained Visual Recognition in Mobile Augmented Reality for Technical Support," in IEEE ISMAR 2020[1, 2], which outlines an augmented reality (AR) solution that our colleagues in IBM Technology Support Services (TSS) use to increase the rate of first-time fixes and reduce the mean time to recovery from a hardware disruption. "The most recent industry surveys have shown that the average enterprise estimates that there is an impact of approximately $8,851 for every minute of unplanned downtime in their primary computing environment." By displaying guidance over the physical environment, augmented reality support uses visual guidance to drastically reduce the effort needed to relay instructions, the number of errors and even the time required to look up service information. Technical support service providers typically maintain tens of thousands of products in order to meet the needs of their clients.

He has extensive experience in the retail & marketing & e-commerce industries with skills that span customer-based strategies & digital transformation. Milton has had a long & successful career spanning a diverse portfolio of industries, including publishing & retail. He was formerly Chief Digital Officer of Retailwinds where he led digital media & e-commerce. Prior to Retailwinds, he was Chief Marketing Officer of Hudson's Bay Company where he oversaw the strategic direction & performance of all marketing efforts for the Company's North American retail banners & led the Marketing Center of Excellence (COE). He joined HBC as the Senior Vice President of Digital Marketing in September 2016.

She works on expanding the reach of IBM's technology to New York City's developer community. Her area of interest includes prototyping with NodeRED & working with AI services to build fun & interesting things! Prior to living in NYC, Pooja lived in Boston, MA where she was working as an API automation engineer in the healthcare tech industry. She mainly works in Javascript & Java, however she tinkers with Python. She is currently passionate about Node-RED & building IoT applications using Node-RED services. She is a strong believer in helping new technologist get up & running with technology & feel confident in their abilities to make!

An image is worth a thousand words says the old wisdom quote that captures the importance of visual analysis in the learning process of human species. Every time we are presented with a visual scene, our brains make thousands of inferences about the objects in it and their contextual nature. For instance, if we see a person sitting down, we will infer that there is a chair underneath him. Visual inferences works even when we can't see the object. For instance, if we see a closet in a bedroom, we would assume there are clothing items inside even when we can't see them.

Two months ago, Facebook's AI Research Lab (FAIR) published some impressive training times for massively distributed visual recognition models. Today IBM is firing back with some numbers of its own. IBM's research groups says it was able to train ResNet-50 for 1k classes in 50 minutes across 256 GPUs -- which is effectively just the polite way of saying "my model trains faster than your model." Facebook noted that with Caffe2 it was able to train a similar ResNet-50 model in one hour on 256 GPUs using an 8k mini-batch approach. This would be a natural moment to question why any of this matters in the first place.