Available 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, says the company, its internal tests show that NeoML offers 15% to 20% faster performance for pre-trained image processing models running on any device. The combination of higher inference speed with platform independence makes the library suited for mobile solutions that require both seamless customer experience and on-device data processing.
"The launch of NeoML reflects our commitment to contribute to industry-wide AI innovation," says Ivan Yamshchikov, AI Evangelist at ABBYY. "Sharing our framework allows developers to leverage its inference speed, cross-platform capabilities, and especially its potential on mobile devices, while their feedback and contribution will grow and improve the library. We are thrilled to promote advancements in AI and support machine learning being applied to increasingly high-value and impactful use cases."
Developers can use NeoML to build, train, and deploy models for object identification, classification, semantic segmentation, verification, and predictive modeling in order to achieve various business goals. For instance, says the company, banks can develop models to manage credit risk and predict customer churn; telecom companies to analyze the performance of marketing campaigns; retail and fast-moving consumer goods (FMCG) to build remote client identification with face recognition and data verification.
NeoML is designed as a universal tool to process and analyze data in a variety of formats including text, image, video, and others. It supports C++, Java, and Objective-C programming languages; Python will be added shortly. NeoML's neural network models support over 100 layer types. It also offers 20+ traditional ML algorithms such as classification, regression, and clustering frameworks. The library is fully cross-platform – a single code base that can be run on all popular operating systems including Windows, Linux, macOS, iOS, and Android – and optimized for both CPU and GPU