Basics Python |
Basic Tutorial: Introduction, Installation, Environment Setup, Basic Syntax, Variable Types, Basic Operators, Decision, Making, Loops, Numbers, Strings, Lists, Tuples, Dictionary, Date & Time, Functions, Modules, Files I/O, Exceptions. |
Day 2: Data Processing |
Numpy |
Introduction, Installation, Environment, Ndarray Object, Data Types, Array Attributes, Array from Existing Data, Array From Numerical Ranges, Indexing & Slicing, Broadcasting, Iterating Over Array, Array Manipulation, Binary Operators, String Functions, Arithmetic Operations. |
Scipy |
Introduction, Installation, File input/output, Special functions, Linear algebra operations, Fast Fourier transforms, Optimization and fit, Statistics and random numbers, Interpolation, Numerical integration, Signal processing, Image processing |
Day 3: Data Manipulation and Visualization |
Pandas |
Introduction, Installation, Object Creation, Viewing Data, Selection (Getting, Selection by Label, Selection by Position, Boolean Indexing, Setting), Missing Data, Operations (Stats, Apply, Histogramming, String Methods), Merge (Concat, Join, Append), Grouping, Reshaping (Stack, Pivot Tables), Time Series, Categoricals, Plotting |
Matplotlib |
Introduction, Installation, Plotting with default settings, Instantiating defaults, Changing colors and line widths, Setting limits, Setting ticks, Setting tick labels, Moving spines, Adding a legend, Figures, Subplots, Axes, Ticks, Regular Plots, Scatter Plots, Bar Plots. |
Day 4: Multimedia Data Pre-processing |
Images |
Binarize Images, Blurring Images, Cropping Images, Detect Edges, Enhance Contrast Of Color Image, Enhance Contrast Of Greyscale Image, Harris Corner Detector, Installing OpenCV, Isolate Colors, Load Images, Remove Backgrounds, Save Images, Sharpen Images, Shi-Tomasi Corner Detector, Using Mean Color As A Feature. |
Text |
Bag of Words, Parse HTML, Remove Punctuation, Remove Stop Words, Replace Characters, Stemming Words, Strip Whitespace, Tag Parts Of Speech, Term Frequency Inverse Document Frequency |
Day 5: Machine Learning and Deep Learning |
Scikit Learn |
- Introduction and Preparation: Data formats, preparation, and representation, Supervised learning: Training and test data, Estimators for classification, Estimators for regression analysis. Clustering, the scikit-learn estimator interface,
- Models: Cross-Validation, Model complexity and grid search for adjusting hyperparameters, Scikit-learn Pipelines, Performance metrics for classification, Linear Models, Support Vector Machines, Decision trees and random forests, and ensemble methods, feature selection
|
Keras |
- Basics: Introduction, logistic regression, multilayer perceptron, Deep Neural Networks.
- Deep Learning Models: Convolutional Neural Networks, Recurrent Neural Networks, Auto encoder
- Applications: Image Classification, Text Classification
|