K.K. BEST PATH RESEARCH.
All rights reserved.
Both our founders got started in Machine Learning long before the recent renewed interest in AI and Deep Learning. Both wrote and trained their first neural networks for recognizing hand-written digits in the early 1990s.
Deep Learning is an amazing set of technologies and is often the best choice for a given task when sufficient data is available. However, sometimes there simply isn’t enough data to train an accurate model, or the deployment target has insufficient power or energy resources for a Deep Learning solution. In such cases, a more traditional machine learning approach may be more suitable. Our team can advise on which technologies are best for your use case, not limiting the possibilities to only AI and Deep Learning.
Where we feel a Deep Learning solution is likely to be the best approach we can advise on every aspect of system development, from data collection and annotation, through to training, evaluation and deployment.
Each member of our software development team has many years of experience developing software applications at large companies primarily using C, C++ and Python, among other languages. Their proven track record of deployed applications ranges from Linux services running in the cloud, to embedded applications running on iOS, Android and Raspberry Pi.
We have worked extensively with Tensorflow and PyTorch, both for training and deployment, using both the C++ and Python APIs. But our team’s knowledge and skills are not just limited to Deep Learning. A non-exhaustive list of the technologies we have extensive hands-on experience with include:
ROS2 – the go-to open source Robotics toolkit
OpenCV – the definitive open-source toolkit for Computer Vision
Our team can advise on the most suitable data for your task, selecting from pre-existing data sources, when available, to generating artificial data where feasible, to collecting and annotating real-world data, when necessary.
If you have your own data we can advise you on how it should be pre-processed and annotated. Or you can leave everything to our team of annotators, each of whom has many years experience annotating large volumes of both image, text and audio data.