Design and development of CNN models according to the business objective, along with metrics to track their progress.
Optimize the CNN models in terms of trainable parameters and MAC operations to meet the target platform.
Debug the intermediate as well as final layer output of trained model using various explainable AI methods.
Extend existing ML libraries and frameworks to support missing layers or other features.
Exploring and visualizing data to gain an understanding of it, then identifying differences in data distribution that could affect performance when deploying the model in the real world
Verifying data quality, and/or ensuring it via data cleaning
Supervising the data acquisition process if more data is needed
Defining the pre-processing or feature engineering to be done on a given dataset
Defining data augmentation pipelines
Training models and tuning their hyperparameters
Analysing the errors of the model and designing strategies to overcome them
