Certificate
This is a Professional Certificate consisting of 6 courses, each with its own certification. You can check the authenticity by viewing the original certification on Coursera, you can also see all my credentials on LinkedIn. You can also see my badges on Credly.
Course Overview :
Principles : Supervised and Unsupervised learning, and evalutaion metrics. Algorithms : Lineair regression, Regression Trees, Logistic Regression, SVM, and K-Means
Course Overview :
Principles : Deep Learning (DL), Gradient Descent, Backpropagation, Activation functions, Vanishing gradient, Regression with DL, Classification with DL Algorithms : ANN, CNN, RNN, Autoencoders
Course Overview :
Principles : Computer Vision, Image Processing and manipulation, Image Classification, Object Detection (Haar, Faster R-CNN). Details : Pillow, OpenCV, geometric operations, histograms & tensity transformation, spatial feltering, Batching, Data Augmentation, Momentum, CNN architectures.
Course Overview :
Principles : Pytorch, Differentiation in Pytorch, Derivatives in Pytorch, Dataset manipulation in Pytorch, Optimization in Pytorch, DNN with Pytorch, Initialization (Xavier, He, NN). Other Concepts : Dropouts, Batch Normalization, Max Pooling.
Course Overview :
Principles : TensorFlow, tf 2.x and eager execution, Linear Regression with Tf, Logistic Regression with Tf, sequential. algorithms : RNN, LSTM, RBMs, Autoencoders.
Course Overview :
Capstone Project : This is the final project focusing on image classification using the ResNet50 architecture. Accomplishments: Data loading, visualization of the image dataset, data preparation (including manipulation and analysis), building the classifier model, and finally, evaluation and testing.