Udemy - Mathematics For Machine Learning And Llms

[Courses2024 0]

Free Download Udemy - Mathematics For Machine Learning And Llms
Published: 3/2025
MP4 | Video: h264, 1920x1080 | Audio: AAC, 44.1 KHz
Language: English | Size: 2.81 GB | Duration: 15h 28m
How is math used in AI

What you'll learn
Machine Learning mathematics
linear algebra, statistics, probability and calculus for machine learning
How algorithms works
How algorithms are parametrizided
Requirements
Basic notions of machine learning
Description
Machine Learning is one of the hottest technologies of our time! If you are new to ML and want to become a Data Scientist, you need to understand the mathematics behind ML algorithms. There is no way around it. It is an intrinsic part of the role of a Data Scientist and any recruiter or experienced professional will attest to that. The enthusiast who is interested in learning more about the magic behind Machine Learning algorithms currently faces a daunting set of prerequisites: Programming, Large Scale Data Analysis, mathematical structures associated with models and knowledge of the application itself. A common complaint of mathematics students around the world is that the topics covered seem to have little relevance to practical problems. But that is not the case with Machine Learning.This course is not designed to make you a Mathematician, but it does provide a practical approach to working with data and focuses on the key mathematical concepts that you will encounter in machine learning studies. It is designed to fill in the gaps for students who have missed these key concepts as part of their formal education, or who need to catch up after a long break from studying mathematics.Upon completing the course, students will be equipped to understand and apply mathematical concepts to analyze and develop machine learning models, including Large Language Models.
Overview
Section 1: Introduction
Lecture 1 Introduction
Lecture 2 The Learning Diagram
Lecture 3 Python
Section 2: Types of Learning
Lecture 4 Supervised Learnimg
Lecture 5 Unsupervised Learning
Lecture 6 Reinforcement Learning
Lecture 7 When to Use and Not to Use ML
Lecture 8 How to chose ML Algorithms
Section 3: Data Preparation
Lecture 9 Preeliminar Analysis
Lecture 10 The Target Variable
Lecture 11 Missing Data
Lecture 12 Log Transformation - Homocedasticity
Lecture 13 Outliers and Anomaly Detection
Lecture 14 Data Transformation
Lecture 15 Data Transformation (cont.)
Section 4: Statistics in the Context off ML
Lecture 16 Significant Differences
Lecture 17 Descriptive and Inferential Statistics
Section 5: Descriptive Statistics
Lecture 18 Variables and Metrics
Lecture 19 Correlation and Covariance
Section 6: Probabilities for ML
Lecture 20 Uncertainity
Lecture 21 Frquentist versus Bayesian Probabilities
Lecture 22 Random Variables and Sampling
Lecture 23 Sampling Spaces
Lecture 24 Basic Definitions of Probabilities
Lecture 25 Axions, Theorems, Independence
Lecture 26 Conditional Probability
Lecture 27 Bayes Theorem and Naive Bayes Algorithm
Lecture 28 Expectation, Chance and Likelihood
Lecture 29 Maximum Likelihood Estimation (MLE)
Lecture 30 Simulations
Lecture 31 Monte Carlo Simulation, Markov Chainn
Lecture 32 Probability Distributions
Lecture 33 Families of Distributions
Lecture 34 Normal Distribution
Lecture 35 Tests for Normality
Lecture 36 Exponential Distribution
Lecture 37 Weibull Distribution and Survival Analysis
Lecture 38 Binomial Distribution
Lecture 39 Poisson Distribution
Section 7: Statiscs Tests
Lecture 40 Hypothesis Testing
Lecture 41 The p- value
Lecture 42 Critical Value, Significance, Confidence, CLT, LLN
Lecture 43 Z and T Tests
Lecture 44 Degrees of Freedom and F statistics
Lecture 45 ANOVA
Lecture 46 Chi Squared Test
Lecture 47 Statistical Power
Lecture 48 Robustness and Statistical Sufficiency
Section 8: Time Series
Lecture 49 Times Series Decommposition
Lecture 50 Autoregressive Models
Lecture 51 Arima
Section 9: Linear ad Non Linear Models
Lecture 52 Linear and Non Linear Models
Section 10: Linear Algebra for ML
Lecture 53 Introduction to Linear Algebra
Lecture 54 Types of Matrices
Lecture 55 Matrices Operations
Lecture 56 Linear Transformations
Lecture 57 Matrix Decomposition and Tensors
Section 11: Calculus for ML
Lecture 58 Functions
Lecture 59 Limits
Lecture 60 The Derivative
Lecture 61 Calculating the Derivative
Lecture 62 Maximum and Minimum
Lecture 63 Analitical vs Numerical Solutions
Lecture 64 Numerical and Analytic Solution
Lecture 65 Gradient Descent
Section 12: Distances, Similarities, knn and k means
Lecture 66 Distance Measurements
Lecture 67 Similarities
Lecture 68 Knn and K means
Lecture 69 Distances in Python
Section 13: Training, Testing ,Validation
Lecture 70 Training, Testin, Validation
Lecture 71 Training, Testing, Validation (cont)
Section 14: The Cost Function
Lecture 72 The Cost Function
Lecture 73 Cost Function for Regression and Classification
Lecture 74 Minimazing the Cost Function with Gradient Descent
Lecture 75 Batch annd Stochastic Gradient Descent
Section 15: Bias and Variance
Lecture 76 Bias and Variance Introduction
Lecture 77 Complexity
Lecture 78 Regularization
Lecture 79 Regularization (Cont)
Section 16: Parametric andd Non Parametric Algorithms
Lecture 80 Parametric and Non Parametric Algorithms
Section 17: Learning Curves
Lecture 81 Learning Curves
Lecture 82 Learning Curves in Python
Section 18: Dimensionality Reduction
Lecture 83 PCA and SCD
Lecture 84 Eigenvectors and Eigenvalues
Lecture 85 Dimensionality Reduction in Python
Section 19: Entropy and Information Gain
Lecture 86 Entropy and Information Gain
Lecture 87 Entropy and Information Gain (cont)
Section 20: Linear Regression
Lecture 88 Linear Regression
Lecture 89 Linear Regression (cont)
Lecture 90 Polinomial Regression
Section 21: Classification
Lecture 91 Logistic Function
Lecture 92 Generalized Linear Models (GLM)
Lecture 93 Decision Boundaries
Lecture 94 Confusion Matrix
Lecture 95 ROC and AUC
Lecture 96 Visualization of Class Distribution
Lecture 97 Precision and Recall
Section 22: Decision Trees
Lecture 98 Introduction to Decision Trees
Lecture 99 Gini Index
Lecture 100 Hyperparameters
Lecture 101 Decision Trees in Python
Section 23: Suport Vector Machines
Lecture 102 Introduction to SVMs
Lecture 103 Introduction to SVMs (cont)
Lecture 104 Mathematics of SVMs
Lecture 105 SVM in Python
Section 24: Ensemble Algorithms
Lecture 106 Wisdom of the Crowds
Lecture 107 Bagging and Random Forest
Lecture 108 Adaboost, Gradient Boosting, XGBoosting
Section 25: Natural Language Processing
Lecture 109 Introduction to NLP
Lecture 110 Tokenization and Embeddings
Lecture 111 Weights and Representation
Lecture 112 Sequences and Sentiment Analysis
Section 26: Neural Networks
Lecture 113 Mathematical Model of Artificial Neuron
Lecture 114 Activation Functions
Lecture 115 Activation Functions (cont)
Lecture 116 Weights and Bias Parameters
Lecture 117 Feedforward and Backpropagation Concepts
Lecture 118 Feedforward Process
Lecture 119 Backpropagation Process
Lecture 120 Recurent Neural Networks (RNN)
Lecture 121 Convolution Neural Networks (CNN)
Lecture 122 Convolution Neural Networks (CNN) (cont)
Lecture 123 Seq2Seq and Aplications of NN
Section 27: Large Language Models
Lecture 124 Generative vs Descriptive AI
Lecture 125 LLMs Properties
Section 28: Transformers
Lecture 126 Introduction to Transformers
Lecture 127 Training and Inference
Lecture 128 Basic Arquitecture of Transformers
Lecture 129 Encoder Workflow
Lecture 130 Sel Attention
Lecture 131 Multi-Head Attention
Lecture 132 Normalization and Residual Connections
Lecture 133 Decoder
Lecture 134 Types of Transformers Arquitecture
Data Scientists and AI professionals
Homepage:

Ukryta Zawartość

Treść widoczna tylko dla użytkowników forum DarkSiders. Zaloguj się lub załóż darmowe konto na forum aby uzyskać dostęp bez limitów.

DOWNLOAD NOW: Udemy - Mathematics For Machine Learning And Llms

Ukryta Zawartość

Treść widoczna tylko dla użytkowników forum DarkSiders. Zaloguj się lub załóż darmowe konto na forum aby uzyskać dostęp bez limitów.

No Password - Links are Interchangeable