วีดีโอ

Deep Sequence Modelling

Convolutional Neural Networks

Machine Learning project strategy for optimizing an objective including Orthogonalization, Single Number Evaluation Metrics, Optimizing and Satisficing Metrics, Training, Dev (Validation) and Test Sets, changing the Metric Function for unexpected scenarios, Accuracy Level Benchmarks including Bayes Optimal Error, Human-level Performance, Variance and Avoidable Bias, and optimization decisions b...

Effect of scaling features, problems of Vanishing Gradient and Exploding Gradient problems, the techniques to solve the problems including, properly initializing weights (Xavieror He initialization), Gradient Clipping, and using proper Activation Functions (e.g.: ReLU), Batch Normalization, Layer Normalization, alternative deep learning architectures (e.g.: LSTM or GRU for RNNs) and deep learni...

Shallow Neural Networks

Neural Network Basics

Learn about Natural Neurons, Neural Networks, Artificial Neural Networks (ANNs), mathematical approximation of ANNs, Activation Functions, Neural Network Types, Single Layer Perceptron, Multi-Layer Perceptron, advantages of Deep Learning, Feature Hierarchies, trend of Deep Learning, and Deep Learning applications.

Learn about Bayesian thinking, Bayes Theorem, Prior, Likelihood, Posterior, Conditional Independence, Naive Bayes, Naive Bayes Classifier Regularization, Laplace Smoothing, Lidstone Smoothing, Bayesian Networks (Bayesian Belief Networks), Bayesian Linear Regression, and Bayesian Optimization.

Learn about Support Vector Machines, Support Vectors, Hard SVM, Soft SVM, Primal Problem, Dual Problem, Regularization, Kernel Trick, Kennel Function, Gaussian Function/Radial Basis Function (RBF), Linear Kernel, Polynomial Kernel, and Support Vector Regression (SVR).

Learn Data Balancing, Hyperparameter Tuning with Grid Search and Random Search, ML model evaluation, ML Performance Metrics, measure of performance of Classification Models, Confusion metrics, Accuracy, Precision, Recall (Sensitivity), Specificity, F-Measures, F1 score, ROC curves, AUC and Cross Validation.

Learn Decision Trees (DT), Building Decision Trees, Optimizing Decision Trees, CART Algorithm, Gini Index, Entropy, Decision Tree Classification Geometry, Converting Continuous Features to Categorical, Bias-Variance Metrics of Decision Tree, Decision Tree Regularization, Ensemble Methods, Bootstrapping, Bagging, Boosting, Random Forrest, and XGBoost.

Learn about the Gradient Descent algorithm for the example of Linear Regression, its parameter initialization, update rule, derivation and introduction to Batch Gradient Descent, Stochastic Gradient Descent and Mini-Batch Gradient Descent optimization.

Learn about Linear Regression, Mean Squared Error (MSE), Linear Regression, R-squired, Multiple Linear Regression, Simple Linear Regression, Linearity assumptions, Homoscedasticity, Multicollinearity, Variance Inflation Factor (VIF), Training and testing, Residual Sum of Squares, Total Sum of Squares, Polynomial Regression and Multivariate Polynomial Regression.

Learn Exploratory Data Analytics with Pandas

Introduction to Statistical & Machine Learning

Deep Learning for NLP

Status of Deep Learning

Large Language Models

Deep Reinforcement Learning

Deep Generative Models

Transformers

Advanced Learning Techniques

Deep Sequence Models

KNN and Clustering

Feature Engineering and Optimization

Bias, Variance and Regularization

Logistic Regression

Introduction to Machine Learning

CNN Architecture