Udemyalltr

Makine Öğrenmesinin Felsefesi ve Matlab Uygulamaları

Learn machine learning fundamentals & probability theory by building from scratch. No libraries needed! Practical skills for data science.

4.8(30)
197students
7h 40m
Certificate
Mehmet İŞCAN
Mehmet İŞCANAraştırma Görevlisi/Mühendis

Course Content

Makine Öğrenmesinin Felsefesi ve Matlab Uygulamaları is an all-levels Udemy course taught by Mehmet İŞCAN. It runs 7h 40m, is taught in Turkish, and includes a certificate of completion. Learners rate it 4.8 out of 5 from 30 reviews, with 197 students enrolled. It is a paid course, first published June 2020.

Dive into the fascinating intersection of mathematics, machine learning, and artificial intelligence! This course explores the philosophical foundations shaping modern AI, particularly focusing on the impact of analytical philosophy on the field. We'll provide a solid introduction to core theories used in machine learning, with practical insights into coding them from scratch – no reliance on pre-built libraries.

Here's a detailed look at what we'll cover:

  • The Philosophy of Machine Learning & Types of Machine Learning: Understand the philosophical underpinnings of AI and the different approaches within machine learning.
  • Gradient Descent Algorithm: A deep dive into optimization methods, specifically the gradient descent algorithm and its derivatives – essential for training machine learning models.
  • Logistic Regression & Perceptron: Learn how to apply logistic regression for classification tasks and build a simple perceptron – a fundamental building block of neural networks.
  • Neural Networks & Backpropagation: Explore artificial neural network architectures and the backpropagation algorithm – the key to training these powerful models.
  • Probability Theory Fundamentals: Discover the origins and philosophical implications of probability theory.
  • Key Probabilistic Concepts: Master covariance, variance, mean, and other core probabilistic concepts, along with their underlying philosophical basis.
  • Probability Density Functions (PDF): Learn to utilize probability density functions and their implementation in MATLAB.
  • Gaussian Mixture Models (GMM): Explore the use of multiple density functions based on mixture models and their application in MATLAB.
  • Probabilistic Mixture Functions for Classification: Apply probabilistic mixture functions to classification problems with practical MATLAB examples.

This course aims to equip you with a strong theoretical and practical understanding of the mathematical principles driving machine learning and artificial intelligence. We hope this knowledge will serve you well throughout your career!

$ whoami — the devs behind tutorialsearch.io

Want AI in your product? Hire the team behind TutorialSearch.io

LLM features, RAG, agents and automation wired into a real product — built by the devs who shipped this site.

5.0(54)
1h 33m
expert

Rönesans Felsefesi

by Turgay Ovalı

5.0(797)
5h 31m
intermediate
4.9(752)
5h 10m
beginner
4.9(1,297)
4h 40m
intermediate