Machine Learning 0 to 100 | python | Artificial Intelligence

Name: Machine Learning 0 to 100 | python | Artificial Intelligence
Rating: 4.2 (6 reviews)

Created byGhazal Lalooha

Last updated 2/2025

English

English [Auto],

What you'll learn

Understand the Fundamentals of Machine Learning: Define ML and differentiate it from traditional programming, explain the types of ML: Supervised, Unsupervised
Identify Real-World applications of ML:Recognize various applications of ML across different industries, Discuss case studies of successful ML implementations.
Grasp key ML terminology and concepts: Understand key terms: features, labels, models, training, testing, overfitting, underfitting, model evaluation metrics
Comprehend Various ML Algorithms: Learn the principles of different algorithms (linear regression, decision trees, support vector machines and neural networks)
Master data collection and preprocessing techniques: Learn methods for gathering data from various sources, understand techniques for cleaning, normalizing data
Implement data visualization for insights: Create and interpret visualizations using libraries such as Matplotlib, Use visual tools to identify patterns,trends
Develop proficiency in Python for ML: write efficient and readable python code using best practices, Utilize key Data Science libraries (NumPy,pandas,...)
Evaluate and interpret ML models: Utilize metrics(accuracy, precision, recall, F1-score and ROC-AUC), Conduct thorough error analysis
Implement model tuning techniques: Apply cross-validation, grid search, and random search to find optimal model parameters,Use ensemble models(bagging,boosting)
Address Common Issues in ML:Identify and solve problems(data imbalance, high dimensionality, and multicollinearity),Implement techniques to handle missing data
Understand the Deployment of ML models: Learn the steps and best practices for deploying models into production environments

Coding Exercises

This course includes our updated coding exercises so you can practice your skills as you learn.

Course content

2 sections • 20 lectures • 5h 39m total length

Introduction19:32
Explore the fundamentals of machine learning, including supervised, unsupervised, and reinforcement learning, with practical Python-driven examples like spam detection and regression vs. classification tasks.
Supervised Learning and Linear Regression24:16
Explore supervised learning with linear regression, cost functions, and gradient descent to map inputs to outputs, train hypotheses, and predict continuous targets like house prices while distinguishing regression from classification.
Linear Regression and Gradient Descent24:57
Explore the gradient descent algorithm for univariate linear regression, minimize the cost function, and update theta zero and theta one with learning rate alpha to reach the global optimum.
Local Regression12:38
Learn local regression, a non-parametric method that weights nearby data with a bell-shaped function to predict x, highlighting distance-based importance over all data.
Python for ML13:03
Explains Python basics for machine learning, emphasizes numpy arrays, matrices, and vectors; introduces Jupyter notebooks and Anaconda, common commands (linspace, ones, zeros, randn), and practice to master ML concepts.
Python for ML(2)13:21
Explore foundational Python concepts for machine learning, including numpy arrays, vectors and matrices, data structures, and random and plotting libraries, with hands-on practice in Jupyter notebooks via Anaconda.
Python for ML(3)12:05
Learn Python for machine learning with matrices, NumPy operations (concatenation, stacking, broadcasting, transpose, elementwise and dot products), and Matplotlib visualizations.
Python for ML(4)7:56
Master Python control structures and conditional statements for machine learning, including coin toss probability demonstrations, loops, and functions with proper indentation and vectorized, modular design.
Logistic Regression22:32
Learn how logistic regression uses the sigmoid function to map inputs to probabilities, apply a threshold for binary classification, and optimize with convex log-likelihood cost functions and gradient descent.
Overfitting and Regularization18:05
Explore how overfitting arises with high model complexity and learn how regularization, including L1, L2, and elasticnet, helps balance training fit and generalization to data in linear and neural networks.
Softmax Classifier and Neural Networks22:13
Explore softmax classifiers for multi-class neural networks, converting scores to probability distributions with softmax, training via cross-entropy loss and gradient descent, with one-hot encoding and regularization.
Artificial Neural Networks and Backproragation Algorithm15:00
Explore artificial neural networks with hidden layers and a multi-layer perceptron, learn forward and backward propagation, activation functions like sigmoid, hyperbolic tangent, and ReLU, and apply regularization to combat overfitting.
Artificial Neuarl Network - training16:26
Explore advanced neural network training techniques, including vectorizing parameters, gradient checking, and mini-batch descent, and compare with margin-based support vector machines.
Support Vector Machines18:24
Explore support vector machines and soft margin optimization using Lagrange multipliers, alpha, and kernels to transform nonlinear data into separable spaces.
Kernel Functions and Model Selections16:10
Explore kernel functions and model selection in SVM, contrasting polynomial kernels of degree two mapped to six features with gaussian kernels, using cross-validation and grid search in scikit-learn.
Unsuppervised Learning and Clustering15:44
Learn unsupervised learning through clustering with K-means, including initialization, distance calculations, objective optimization, elbow method, dimension reduction, and post-processing techniques for market segmentation and recommender systems.
Dimentionality Reduction20:06
Explore unsupervised dimensionality reduction with PCA to reduce data dimensions while preserving information for preprocessing and compression.
Anomaly Detection23:58
Learn anomaly detection in unsupervised learning using Gaussian distributions, density estimation, and thresholds to identify outliers. Apply features, independence assumptions, and probability-based scoring to distinguish normal from abnormal data.
Anomaly Detection (2)5:28
Explore anomaly detection using multivariate Gaussian distributions, estimating mean and covariance, analyzing correlations and diagonal cases, and identifying outliers via probability thresholds in Python.
Recommender Systems17:57
Explore recommender systems using user- and product-based collaborative filtering, similarity measures (Pearson, cosine), and matrix decomposition with svd. Learn about cold start, normalization, and online updates.
Supervised Learning- outlier prediction
TP, FP, FN, TN calculation
Quiz1
Quiz2
Quiz3
Quiz4
Quiz5
Quiz6
Quiz7
Quiz8
Quiz9
Quiz10
Quiz11
Quiz12
Quiz13
Quiz14
Quiz15

Requirements

familiarity with Python programming language
familiarity with linear algebra (recommended but not needed)

Description

Mastering Machine Learning from concepts to real-world coding.

Unlock the power of Machine Learning and accelerate your career with this comprehensive course, designed to bridge the gap between theory and practical applications. Whether you're an aspiring data scientist, a seasoned developer, or a business professional looking to harness the capabilities of Machine Learning, this course will equip you with the tools and knowledge you need to excel.

What you will learn:

-Foundation of Machine Learning: You will understand the core concept and terminology

-Algorithms and Models: You will dive deep into various Machine Learning algorithms

-Data preprocessing: You will master techniques like Data Cleaning, Normalization, Feature Engineering, and Feature Selection to prepare your data for analysis.

-Practical coding exercise: You will gain proficiency in Python and essential data science libraries.

-Model evaluation and tuning: You will learn to evaluate and interpret models using metrics like accuracy, precision, recall, and ROC-AUC. You will learn to Tune your model using cross-validation and hyperparameter optimization.

-Real-world coding exercises: You will apply what you've learned through hands-on projects that simulate real-world scenarios, from data collection to model deployment.

-Problem-solving techniques: You will address common issues like data imbalance, high dimensionality, and overfitting with practical solutions.

Course Highlights:

-Interactive lessons and real projects

-Expert instructions

-Hands-on approach

-Comprehensive Resources

Who this course is for:

everyone who wants to get promotion in his job(in every field of work)
everyone who doesn't want to be laid of his/her position at work