by Modzy | Jan 6, 2023 | Uncategorized
There are many different types of hardware that can accelerate ML computations – CPUs, GPUs, TPUs, FPGAs, ASICs, and more. Learn more about the different types, when to use them, and how they can be used to speed up ML inference and the performance of ML...
by Modzy | Dec 9, 2022 | Uncategorized
At Modzy we’ve developed a microservices based model operations platform that accelerates the deployment, integration, and governance of production-ready AI. Modzy is built on top of Kubernetes, which we selected for its scheduling, scalability, fault tolerance, and...
by Modzy | Nov 4, 2022 | Uncategorized
Developing and deploying AI-powered systems and applications is a complex business, especially in our extended remote reality. You’re likely facing an uphill climb and let’s face it, huge risks. The way to clear the obstacles, lower the risks, and raise the value you...
by Modzy | Sep 19, 2022 | Uncategorized
It’s estimated that anywhere from 50-90% of AI models developed never make it past the AI “valley of death” that exists between the lab and production deployment. This tech talk covers how an API-based approach to building and maintaining AI-enabled applications can...
by Modzy | Aug 26, 2022 | Uncategorized
Data drift occurs when a model sees production data that differs from its training data. If a model is asked to make a prediction based upon drifted data, the model is unlikely to achieve its reported performance. This phenomenon happens because during training, a...
Recent Comments