To achieve full understanding of the use and application of ML algorithms, our participants will work on a real-life industry project, translating theoretical knowledge to practical process and overcoming realistic challenges.
Scope:~400 work hours total
Data:Real data provided by company
Guidance:Experienced mentors provided by Y-DATA
Support:Weekly meetings with company data-owner
1 / 10
Trigo empowers grocery retailers to seamlessly eliminate the industry's leading consumer pain point -- checkout -- through a world-leading computer vision and AI-based system. Accurately predicting human poses is crucial for a smoothly functioning autonomous store. However, annotating data for pose estimation is an extremely expensive endeavor. Thus, improving algorithms by utilizing unused, unlabeled data is of great importance and can make a significant difference, especially if it can be applied in crowded environments. This project takes a novel approach, applying semi-supervised methods to the task of pose estimation. The project’s goal is to use self- and semi-supervised methods and convolutional neural networks to harness unlabeled multi-person images towards improving pose estimation with a limited amount of labeled data.
1 / 0
The process of working on the project follows popular industry standards and methodologies and incorporates a growing set of tools the students possess to methodically understand and solve a real-world problem. Our students have a full-cycle data science project in their portfolio upon graduation, covering all industry-standard stages: Business Understanding, Data Understanding, Data Preparation, Modeling, Evaluation.
Example ProjectAutomatic detection of low-value queries in technical Q&A forum
A customer operates a forum where programmers ask each other questions, provide answers and rate questions giving them \"ups\" and \"downs\". The forum has a core expert community that provides good answers and valuable insights. However, they often waste their time handling questions of little to no value: marking questions as duplicates and redirecting them, closing topics with incoherent or irrelevant questions etc. Because of this, the overall efficiency of the system suffers.