Download Udemy – (2023) Machine Learning and Deep Learning Bootcamp in Python 2022-8

Description

Course 2023 Machine Learning and Deep Learning Bootcamp in Python. Interested in machine learning, deep learning and computer vision? Then this course is right for you! This course is about the basic concepts of machine learning, deep learning, reinforcement learning and machine learning. These topics are very hot nowadays because these learning algorithms can be used in several fields from software engineering to investment banking. In each section, we will talk about the theoretical background of all these algorithms, then we will implement these problems together. We will use Python with SkLearn, Keras and TensorFlow.

### machine learning ###

1.) Linear regression

• Understanding the linear regression model
• Correlation and covariance matrix
• Linear relationships between random variables
• Gradient descent and design matrix approaches

2.) Logistic regression

• Understanding logistic regression
• Principles of classification algorithms
• Maximum likelihood function and estimation

3.) K-Nearest Neighbors Classifier

• What is the k-nearest neighbor classifier?
• Nonparametric machine learning algorithms

4.) Simple Bayes Algorithm

• What is Simple Bayes Algorithm?
• Classification based on probability
• Cross validation
• Too much and too little

5.) Support Vector Machines (SVM)

• Support Vector Machines (SVM) and Support Vector Classifiers (SVC)
• Maximum Margin Classifier
• Core trick

6.) Decision trees and random forests

• Decision tree classification
• Random forest classification
• Composition of weak learners

7.) Backpacking and strengthening

• What is bagging and strengthening?
• AdaBoost algorithm
• Combination of weak learners (swarm intelligence)

8.) Clustering algorithms

• What are clustering algorithms?
• k-means clustering and elbow method
• DBSCAN algorithm
• Hierarchical clustering
• Market segmentation analysis

### Neural networks and deep learning ###

9.) Feed forward neural networks

• Single layer perceptron model
• feed.forward neural networks
• Activation functions
• Back propagation algorithm

10.) Deep Neural Networks

• What are deep neural networks?
• ReLU activation functions and the vanishing gradient problem
• Training deep neural networks
• loss functions (cost functions)

11.) Convolutional Neural Networks (CNN)

• What are convolutional neural networks?
• Feature selection with core
• Feature detectors
• Gather and flatten

12.) Recurrent Neural Networks (RNN)

• What are recurrent neural networks?
• Training of recurrent neural networks
• Explosive gradient problem
• LSTM and GRU
• Time series analysis with LSTM networks

Numerical optimization (in machine learning)

• Gradient Descent Algorithm
• Theory and implementation of stochastic gradient descent
• ADAGrad and RMSProp algorithms
• ADAM optimizer explained
• Implementation of ADAM algorithm

13.) Reinforcement learning

• Markov Decision Processes (MDPs)
• Value repetition and policy repetition
• Exploration versus exploitation problem
• The problem of multi-armed bandits
• Q learning and Q deep learning
• Learning tic-tac-toe with cue learning and deep cue learning

### computer vision ###

14.) Basics of image processing:

• Theory of computer vision
• What are pixel intensity values?
• Complexity and kernels (filters)
• Nucleus blur
• Core sharpening
• Edge detection in computer vision (edge ​​detection kernel)

15.) Surf-driving cars and lane detection

• How to use computer vision approaches in line detection
• Canny Algorithm
• How to use the Hough transform to find lines based on pixel intensity

16.) Face recognition with Viola Jones algorithm:

• Viola Jones approach in computer vision
• What is the sliding windows approach?
• Face recognition in images and videos

17. Algorithm of histogram oriented gradients (HOG).

• How to outperform the Viola Jones algorithm with better approaches
• How to detect gradients and edges in an image
• Making a histogram of directional gradients
• Using support vector machines (SVM) as machine learning algorithms

18. Approaches based on complexity neural networks (CNN).

• What’s wrong with the sliding windows approach?
• Area suggestions and selective search algorithms
• Region-Based Convolutional Neural Networks (C-RNN)
• Fast C-RNNs
• Faster C-RNNs

19. You only look once object detection algorithm (YOLO).

• What is the YOLO approach?
• Making bounding boxes
• How to recognize objects in an image at a glance?
• Union Intersection Algorithm (IOU).
• How to keep the most relevant bounding box with non-maximal suppression?

20.) SDD Object Detection Algorithm of Single Shot Multiple Box Detector (SSD)

• What is the main idea behind the SSD algorithm?
• Construction of anchor box
• VGG16 and MobileNet architecture
• SSD implementation with real-time videos

You get lifetime access to over 150 lectures plus slides and source code for the lectures! So what are you waiting for? Learn machine learning, deep learning, and computer vision in a way that will advance your career and increase your knowledge, all in a fun and practical way!

What you will learn in the 2023 Machine Learning and Deep Learning Bootcamp in Python course

This course is suitable for people who

• This course is intended for beginners unfamiliar with machine learning, deep learning, computer vision, and reinforcement learning, or students looking for a quick refresher.

Details of the 2023 Machine Learning and Deep Learning Bootcamp in Python course

• Publisher: Udemy
• teacher: Holczer Balazs
• Training level: beginner to advanced
• Training duration: 32 hours and 37 minutes
• Number of courses: 339

Headlines of the 2023 Machine Learning and Deep Learning Bootcamp in Python course on 11/2023

Prerequisites for the 2023 Machine Learning and Deep Learning Bootcamp in Python course

• Basic Python – we will use Panda and Numpy as well (we will cover the basics during implementations)

Images of the 2023 Machine Learning and Deep Learning Bootcamp in Python course

Sample video of the course

download link

Download part 1 – 2 GB

Download part 2 – 2 GB

Download part 3 – 2 GB

Download part 4 – 379 MB

File(s) password: www.downloadly.ir

Size

6.37 GB