We typically think of companies competing over products — the proverbial “build a better mousetrap.” But in today’s networked age, competition is increasingly over platforms. Build a better platform, and you will have a decided advantage over the competition.
In construction, a platform is something that lifts you up and on which others can stand. The same is true in business. By building a digital platform, other businesses can easily connect their business with yours, build products and services on top of it, and co-create value. This ability to “plug-and-play” is a defining characteristic of Platform Thinking. Read More
Daily Archives: June 19, 2020
Self-Supervised Relational Reasoning for Representation Learning
In self-supervised learning, a system is tasked with achieving a surrogate objective by defining alternative targets on a set of unlabeled data. The aim is to build useful representations that can be used in downstream tasks, without costly manual annotation. In this work, we propose a novel self-supervised formulation of relational reasoning that allows a learner to bootstrap a signal from information implicit in unlabeled data. Training a relation head to discriminate how entities relate to themselves (intra-reasoning) and other entities (inter-reasoning), results in rich and descriptive representations in the underlying neural network backbone, which can be used in downstream tasks such as classification and image retrieval. We evaluate the proposed method following a rigorous experimental procedure, using standard datasets, protocols, and backbones. Self-supervised relational reasoning outperforms the best competitor in all conditions by an average 14% in accuracy,and the most recent state-of-the-art model by 3%. We link the effectiveness of the method to the maximization of a Bernoulli log-likelihood, which can be considered as a proxy for maximizing the mutual information, resulting in a more efficient objective with respect to the commonly used contrastive losses. Read More
Has Media & Entertainment Cracked the AI Code?
Artificial Intelligence (AI) and Machine Learning (ML) are technologies that enterprises across industries have been keenly experimenting with to explore the utility they can bring. Is there AI adoption within the M&E industry? Can AI be the solution for enterprises seeking automation? Have we cracked the AI code or do we have miles to go? If automation is a goal, it should be a priority even now.
Content recommendation (for OTT), speech-to-text and media recognition are some of the initial applications that have been attempted. Clients find vendor demos to be impressive, but when they do a proof of concept (PoC) with their content, results are not. In video operations, frame accuracy is a necessity and AI models struggle to universally solve for this. And such specific nuances of getting it right, is what makes automation work. After trying multiple vendors, clients conclude that AI data is still not accurate enough to solve specific M&E use cases. However, they remain optimistic about the future possibilities.
So where is the issue? Read More
Algorithms are designing better buildings
When giant blobs began appearing on city skylines around the world in the late 1980s and 1990s, it marked not an alien invasion but the impact of computers on the practice of building design.
Thanks to computer-aided design (CAD), architects were able to experiment with new organic forms, free from the restraints of slide rules and protractors. The result was famous curvy buildings such as Frank Gehry’s Guggenheim Museum in Bilbao and Future Systems’ Selfridges Department Store in Birmingham.
Today, computers are poised to change buildings once again, this time with algorithms that can inform, refine and even create new designs. Even weirder shapes are just the start: algorithms can now work out the best ways to lay out rooms, construct the buildings and even change them over time to meet users’ needs. In this way, algorithms are giving architects a whole new toolbox with which to realise and improve their ideas. Read More
ABBYY Open-Sources NeoML, Machine Learning Library to Develop Artificial Intelligence Solutions
The framework provides software developers with powerful deep learning and traditional machine learning algorithms for creating applications that fuel digital transformation
ABBYY, a Digital Intelligence company, today announced the launch of NeoML, an open-source library for building, training, and deploying machine learning models. Available now on GitHub, NeoML supports both deep learning and traditional machine learning algorithms. The cross-platform framework is optimized for applications that run in cloud environments, on desktop and mobile devices. Compared to a popular open-source library, NeoML offers 15-20% faster performance for pre-trained image processing models running on any device.[1] The combination of higher inference speed with platform-independence makes the library ideal for mobile solutions that require both seamless customer experience and on-device data processing. Read More
PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitization∗
Recent advances in image-based 3D human shape estimation have been driven by the significant improvement in representation power afforded by deep neural networks.Although current approaches have demonstrated the potential in real world settings, they still fail to produce reconstructions with the level of detail often present in the input images. We argue that this limitation stems primarily form two conflicting requirements; accurate predictions require large context, but precise predictions require high resolution. Due to memory limitations in current hardware,previous approaches tend to take low resolution images asinput to cover large spatial context, and produce less precise(or low resolution) 3D estimates as a result. We address this limitation by formulating a multi-level architecture that is end-to-end trainable. A coarse level observes the whole image at lower resolution and focuses on holistic reasoning.This provides context to an fine level which estimates highly detailed geometry by observing higher-resolution images.We demonstrate that our approach significantly outperforms existing state-of-the-art techniques on single image human shape reconstruction by fully leveraging 1k-resolution input images. Read More
How exactly do you identify an AI start-up?
Everyone wants to be an ‘AI start-up’ – but only when it suits them! So, how exactly do you build (and identify) an AI start-up? Read More
Rick's Cafe AI 