Deep Learning Specialization from Coursera
This specialization includes 5 courses: 1_ Neural Networks and Deep Learning 2_ Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization 3_ Structuring Machine Learning Projects 4_ Convolutional Neural Networks 5_ Sequence Models
About Me
I am Electrical Engineering PhD, having done research in biomedical signal processing. I have expertise in discrete mathematics i.e. signals and systems, probability and statistics, digital signal processing. I am also proficient in Artificial Intelligence i.e. machine learning, deep learning (CNN, RNN, ANN). MATLAB, Python PPG, ECG, EEG **Machine Learning** --PPG, ECG, EEG, physiological signals --Supervised Learning: Classification and Regression tasks --Unsupervised Learning: Clustering --Feature Engineering: Feature Relevance, Redundancy and Transformation --Deep Learning: ANN, CNN, RNN, LSTM, ResNet, AutoEncodders **Digital Signal Processing** --FFT, SWT, DWT algorithms --Signal and system properties --Fourier Transform and its properties --Z-Transform and its properties --Sampling, multirate signal processing --Decimation, Interpolation Filters and their polyphase decomposition --Minimum-phase, all-pass, linear-phase systems --Filter Design using impulse invarience and bilinear transformation **Signals and Systems** --Periodic signals, even odd signals --System properties, Properties of LTI system --Fourier Transform, Z-transform --DFT, FFT --Sampling of Continious time signals **Applied Probability** --Bayes Theorem --Theorem of Total Probability --PDF or CDF(Cumulative density function) --Conditional Probability --Statistical Independence **Random Theory** --Random Variables --Functions of Random Variables --Moments and Covarience --Random Distributions --Mean and Standard Deviation --Normal Distribution --Uniform R.V --Characteristic Function --Random processes, Power Spectral Density
