Computational Histopathology
Classifying cell structures and recognizing similar regions in tissue samples.
Building a solution involving machine learning is much more than the model. It is a complex mix of data structures, model training, model integration and architecture. We engage in end-to-end delivery of a machine learning solution tailored to bring product features to life.
There are many NLP APIs and services available today. Some of these services could give 80% accuracy on extraction tasks involving generic data. However, to solve really hard problems involving natural language understanding, especially with proprietary and small data sets, we need to skillfully use machine learning techniques along with traditional NLP algorithms.
Deep learning techniques have given a fillip to computer vision and image processing solutions. However, training models for proprietary and domain-specific data sets is a challenge. We find innovative ways to transform the domain-specific part of a problem into a generic computational problem in order to deliver practical solutions.
Optimization algorithms are the foundation of modern-day machine learning. However, there is a rich history dating back to many decades. We strive to use these fundamental algorithms to deliver solutions to problems involving allocation, balancing, routing.
Classifying cell structures and recognizing similar regions in tissue samples.
Modeling machine breakdown using supervised learning over high dimensional time-series data
Identifying and extracting key concepts, questions in chat conversations/ reviews and recognizing values for domain attributes.
Predicting rental and sale value of homes depending on historical trends and demographics to within 80% of the actual price.
Improving prediction accuracy using an ensemble techniques
Determining the optimal parameters for a system of equations with an end application specific optimization goal.
In this paper a mathematical model to capture and distinguish the latent structure in the articulation of questions is presented.
Many startups wish to incorporate Machine Learning (ML) algorithms in their products. But they do not have large data specific to their business. Our research to tackle this dichotomy shows that one must roll out ML solutions incrementally.
In this research report, we highlight a problem formulation involving multiple sensors that collectively determine "characteristics" of targets in an environment. We show how the formulation can be solved with Lagrangian relaxation.
You can’t fit categorical variables into a regression equation in their raw form in most of the ML Libraries. If it is not included in the modeling, then you do not get an accurate model. It’s crucial to learn the methods of dealing with such variables.
Using Analytics for multi parameter investment worthiness of properties and neighborhoods