Workshop Certificate of Solving -Real-Time Industry Problems with AI Computer Vision by Third Eye Data

This Workshop was conducted by Cognizance, IIT Roorkee in collaboration with Third Eye Data.
The workshop was conducted on the topic of Solving -Real-Time Industry Problems with AI Computer Vision.

Topics covered in this workshop:
Applications of Artificial Intelligence, Machine Learning, and Deep Learning technologies for the real world. One such real-world problem that is covered in this workshop is analyzing the image quality issues in the manufacturing industry.
Using Computer Vision, we have built the below three features:
a. Object Detection: This is an image object detection model which identifies the objects and their location in the image.
b. Occlusion Detection: This model can detect if an object is clearly visible or occluded by any other objects.
c. Blurriness Detection: This model tells us whether the given image is clear enough to see all the components on the pole or not.

Understand the complete end-to-end AI Processes:
1. Model Development
a. Define business and technical requirements
b. Identify various algorithms as per the definitions
c. Perform a lot of experimentation and iteration with all available data sets
d. Explore data to understand the underlying correlations between different variables

2. Model Training
a. Information gathered from the data exploration process will help us to choose the best model
b. Develop the right model by iterating through its parameters and tuning it to get optimal outputs
c. Split the available data into three parts – training, validation, and testing

3. Model Deployment
a. Validate the models based on both human feedback and outcomes analysis
b. Deploy the models for downstream consumption
c. Keep checking the model outcomes for model precision, accuracy and drift purposes.
d. Retrain as and when needed

4. Data Engineering aspects of Model Development
a. Data Collection: Various Data sources (mobile apps, websites, web apps, microservices, IoT devices, etc.) are instrumented to collect relevant data.
b. Data Ingestion: All this data gets collected into a Data Lake.
c. Data Preparation: It is the extract, transform, load (ETL) operation to cleanse, conform, shape, transform, and catalogue the data blobs and streams in the data lake; making the data ready to consume for ML and store it in a Data Warehouse.

5. Model Validation
a. K-fold cross-validation with an independent test data set
b. Leave-one-out cross-validation with an independent test data set
c. Perform a train/validate/test split on the data

Feedback Loop Analysis
This is the process of leveraging the output of an AI system and corresponding end-user actions in order to retrain and improve models over time.