This course aims to teach learners how to use deep learning to decipher doctor's handwriting accurately. The learning outcomes include understanding the data-processing pipeline, predicting handwritten text with confidence levels, and reducing illegible handwritings. The course covers skills such as data mining, image processing, deep learning model building, and natural language processing. The teaching method involves presenting real-life examples, statistics, and the end-to-end pipeline process. The intended audience for this course includes data scientists, AI enthusiasts, and individuals interested in healthcare data processing and AI applications.
Overview
Syllabus
Intro
Business goal
Case 2: the Doctor's Consultation Certificate
Case 1: the Death Certificate
Data pipeline
Mining
Original image
Line segmentation
Baseline
Training set definition
Data quality
Data partitioning: split into text lines
Deep-Learning Model
Ensemble modelling
Model Training Performance
Model accuracy
Prediction confidence levels
Confidence plot
Examples target population
Examples false positives
Statistics false positives
Examples low confidence
Example: type A
Language detection
Certificate type detection
Preprocessing
Training data
Nomenclature code
Date of Consultation
Comparison OCR - Neural Network
The Grid (5)
Some grid examples
Approach
Examples: 2 lines
Training on histogram features
Results number of lines prediction
Reading the lines
Examples: high confidence false predictions
Grid summary
Second challenge: different patterns
Fourth challenge: rotations
Fifth challenge: superposition and readability
Step 1: find the stamp
Intersection over Union
Summary stamp reading
Application Integration
Conclusion
Taught by
Devoxx
Related Courses
-
Introduction to Machine Learning for Finance
-
Launching Machine Learning: Delivering Operational Success with Gold Standard ML Leadership
5.0 -
Deep Learning and NLP with Spark
-
End-to-End Deep Learning Pipeline for Self-Driving Cars
-
Tensorflow and Deep Reinforcement Learning, Without a PhD
-
Word Embeddings from Deep Space Nine using Machine Learning
