How to make model training and re-training faster and cheaper? We envisioned a multi-use AutoML, aiming to create a solution superior to other HPO services in the market.
Created a novel solution for AI/ML for Techila's computing environment.
Used Bayesian optimization, gradient-free optimization, random&grid search as well as reinforcement learning.
Extended the product to a multi-use AutoML with black box optimization capabilities.
Techila Distributed Computing Engine is a next generation compute grid. It is a user-friendly solution that can improve the productivity of users from the research and development to applications that are deployed within production environments.
In this project, Techila wanted to create a novel solution for AI/ML for their computing environment. Together we identified hyperparameter optimization as a potential candidate. Our data scientists started working as part of Techila’s team, aiming to create a solution superior to other HPO services in the market.
Starting with this idea, we also extended the product to a multi-use AutoML with black box optimization capabilities. In practice, it takes in parameters and returns a score, which is used to fine-tune the input parameters. The solution is instantly usable by data science teams, reducing the need for manual processing of parameters. This makes model training and re-training a lot faster and, most importantly, cheaper.
For tech enthusiasts, we used for example Bayesian optimization, gradient-free optimization, random&grid search as well as reinforcement learning to come up with the state-of-the-art solution, with tools like Scikit-Learn, CatBoost, XGBoost, LGBM, Keras/Tensorflow and Pytorch.
When we founded Veracell, we mostly worked on projects in the healthcare domain. Lately we’ve been active on many fronts. Here's a quick summary of what we are working on.
We enable future AI by working out with you how to collect, clean and consolidate your business-critical data assets and turn them into a real-life AI solution.
Akseli has a strong background in developing scalable, cloud native SaaS software with microservices architecture. He is now working on a project in the role of data scientist to forecast demand for products using sales history.
AI Roots is a network that helps its customers succeed in data-related development projects. We are able to quickly provide the right specialists for demanding data and artificial intelligence projects.
We supplemented Kalmar's data science team with specialized expertise in survival models. We developed predictive maintenance tools using lifecycle modeling.
DataKIT develops services to support the marketing of pharmaceutical companies. During the project, we have delivered a web application designed and implemented from start to finish to be used by DataKIT's pilot customers.
Veracell worked with Trustmary on a data and AI strategy print that will enable the company to accelerate the use of artificial intelligence. The result was tangible plans for choosing the direction of development.
We have helped Tietoevry to come up with new business, designed services using user-oriented methods and provided experts to implement technical solutions in the area of healthcare.
PIRKKO®, developed by Integritas, is an application that can be used to improve mental health work with current resources. Veracell is taking the PIRKKO® system to the next level.