Artificial Intelligence, Deep Learning and Computer Vision Masterclass
Learn the Most up to Date Techniques in Data Mining from Regression to Deep Neural Networks and Computer Vision Algorithms
off original price!
The coupon code you entered is expired or invalid, but the course is still available!
This course is about the fundamental concepts of machine learning, focusing on regression, SVM, decision trees and neural networks. These topics are getting very hot nowadays because these learning algorithms can be used in several fields from software engineering to investment banking. Learning algorithms can recognize patterns which can help detect cancer for example or we may construct algorithms that can have a very good guess about stock prices movement in the market.
In each section we will talk about the theoretical background for all of these algorithms then we are going to implement these problems together. We will use Python with Sklearn, Keras and TensorFlow.
- Machine Learning Algorithms: regression and classification problems with Linear Regression, Logistic Regression, Naive Bayes Classifier, kNN algorithm, Support Vector Machines (SVMs) and Decision Trees
- Neural Networks: what are feed-forward neural networks and why are they useful
- Deep Learning: Recurrent Neural Networks and Convolutional Neural Networks and their applications such as sentiment analysis or stock prices forecast
- Computer Vision and Face Detection with OpenCV
Thanks for joining my course, let's get started!
Your Instructor
Holczer Balazs
My name is Balazs Holczer. I am qualified as a physicist and later on I decided to get a master degree in applied mathematics. At the moment I am working as a simulation engineer at a multinational company. I have been interested in algorithms and data structures and its implementations especially in Java since university. Later on I got acquainted with machine learning techniques, artificial intelligence, numerical methods and recipes such as solving differential equations, linear algebra, interpolation and extrapolation. These things may prove to be very very important in several fields: software engineering, research and development or investment banking. I have a special addiction to quantitative models such as the Black-Scholes model, or the Merton-model. Quantitative analysts use these algorithms and numerical techniques on daily basis so in my opinion these topics are definitely worth learning.
Course Curriculum
Introduction
Available in
days
days
after you enroll
Environment Setup
Available in
days
days
after you enroll
Artificial Intelligence Basics
Available in
days
days
after you enroll
### MACHINE LEARNING ###
Available in
days
days
after you enroll
Linear Regression
Available in
days
days
after you enroll
Logistic Regession
Available in
days
days
after you enroll
-
StartWhat is logistic regression? (11:54)
-
StartLogistic regression and maximum likelihood estimation (4:58)
-
StartLogistic regression example I - sigmoid function (11:29)
-
StartLogistic regression example II- credit scoring (10:53)
-
StartLogistic regression example III - credit scoring (5:51)
-
StartMathematical formulation of logistic regression
Cross Validation
Available in
days
days
after you enroll
K-Nearest Neighbor Classifier
Available in
days
days
after you enroll
-
StartWhat is the k-nearest neighbor classifier? (5:52)
-
StartConcept of lazy learning (3:33)
-
StartDistance metrics - Euclidean-distance (6:47)
-
StartBias and variance trade-off (3:51)
-
StartK-nearest neighbor implementation I (7:10)
-
StartK-nearest neighbor implementation II (8:45)
-
StartK-nearest neighbor implementation III (4:12)
-
StartMathematical formulation of k-nearest neighbor classifier
Naive Bayes Classifier
Available in
days
days
after you enroll
-
StartWhat is the naive Bayes classifier? (10:03)
-
StartNaive Bayes classifier illustration (4:24)
-
StartNaive Bayes classifier implementation (4:01)
-
StartWhat is text clustering? (8:55)
-
StartText clustering - inverse document frequency (TF-IDF) (4:42)
-
StartNaive Bayes example - clustering news (14:23)
-
StartMathematical formulation of naive Bayes classifier
Support Vector Machine (SVM)
Available in
days
days
after you enroll
-
StartWhat are Support Vector Machines (SVMs)? (5:19)
-
StartLinearly separable problems (14:10)
-
StartNon-linearly separable problems (6:32)
-
StartKernel functions (9:49)
-
StartSupport vector machine example I - simple (10:50)
-
StartSupport vector machine example II - iris dataset (6:31)
-
StartSupport vector machines example III - parameter tuning (7:17)
-
StartSupport vector machine example IV - digit recognition (10:04)
-
StartSupport vector machine example V - digit recognition (5:43)
-
StartAdvantages and disadvantages (2:32)
-
StartMathematical formulation of Support Vector Machines (SVMs)
Decision Trees
Available in
days
days
after you enroll
-
StartDecision trees introduction - basics (7:43)
-
StartDecision trees introduction - entropy (8:56)
-
StartDecision trees introduction - information gain (7:51)
-
StartThe Gini-index approach (10:00)
-
StartDecision trees introduction - pros and cons (2:31)
-
StartDecision trees implementation I (5:50)
-
StartDecision trees implementation II - parameter tuning (4:28)
-
StartDecision tree implementation III - identifying cancer (4:49)
-
StartMathematical formulation of decision trees
Random Forest Classifier
Available in
days
days
after you enroll
-
StartPruning introduction (6:56)
-
StartBagging introduction (7:49)
-
StartRandom forest classifier introduction (5:36)
-
StartRandom forests example I - iris dataset (4:14)
-
StartRandom forests example II - credit scoring (3:29)
-
StartRandom forests example III - OCR parameter tuning (9:49)
-
StartMathematical formulation of random forest classifiers
Boosting
Available in
days
days
after you enroll
-
StartBoosting introduction - basics (4:18)
-
StartBoosting introduction - illustration (5:40)
-
StartBoosting introduction - equations (7:13)
-
StartBoosting introduction - final formula (8:27)
-
StartBoosting implementation I - iris dataset (6:29)
-
StartBoosting implementation II -wine classification (11:46)
-
StartBoosting vs. bagging (3:08)
-
StartMathematical formulation of boosting
Principal Component Analysis (PCA)
Available in
days
days
after you enroll
Clustering
Available in
days
days
after you enroll
-
StartK-means clustering introduction (9:57)
-
StartK-means clustering example (7:49)
-
StartK-means clustering - text clustering (9:01)
-
StartDBSCAN introduction (6:25)
-
StartDBSCAN example (8:43)
-
StartHierarchical clustering introduction (6:33)
-
StartHierarchical clustering example (8:10)
-
StartHierarchical clustering - market segmentation (9:34)
-
StartMathematical formulation of clustering
Computer Vision - Face Detection
Available in
days
days
after you enroll
-
StartComputer vision introduction (3:49)
-
StartViola-Jones algorithm (10:53)
-
StartHaar-features (8:31)
-
StartIntegral images (6:22)
-
StartBoosting in computer vision (6:18)
-
StartCascading (4:13)
-
StartFace detection implementation I - installing OpenCV (2:50)
-
StartFace detection implementation II - CascadeClassifier (9:58)
-
StartFace detection implementation III - CascadeClassifier parameters (4:06)
-
StartFace detection implementation IV - tuning the parameters (4:51)
-
StartFace detection implementation V - detecting faces real-time (5:22)
Machine Learning Project I - Face Recognition
Available in
days
days
after you enroll
### NEURAL NETWORKS AND DEEP LEARNING ###
Available in
days
days
after you enroll
Feed-Forward Neural Network Theory
Available in
days
days
after you enroll
-
StartArtificial neural networks - inspiration (5:20)
-
StartArtificial neural networks - layers (4:42)
-
StartArtificial neural networks - the model (5:09)
-
StartWhy to use activation functions? (6:46)
-
StartNeural networks - the big picture (9:07)
-
StartUsing bias nodes in the neural network (1:44)
-
StartHow to measure the error of the network? (4:46)
-
StartOptimization with gradient descent (8:28)
-
StartGradient descent with backpropagation (6:33)
-
StartBackpropagation explained (12:15)
-
StartMathematical formulation of feed-forward neural networks
Single Layer Networks Implementation
Available in
days
days
after you enroll
Deep Learning
Available in
days
days
after you enroll
Deep Neural Networks Theory
Available in
days
days
after you enroll
Deep Neural Networks Implementation
Available in
days
days
after you enroll
Machine Learning Project II - Smile Detector
Available in
days
days
after you enroll
Convolutional Neural Networks (CNNs) Theory
Available in
days
days
after you enroll
-
StartConvolutional neural networks basics (6:04)
-
StartFeature selection (4:11)
-
StartConvolutional neural networks - kernel (4:16)
-
StartConvolutional neural networks - kernel II (5:42)
-
StartConvolutional neural networks - pooling (5:47)
-
StartConvolutional neural networks - flattening (4:59)
-
StartConvolutional neural networks - illustration (2:38)
-
StartMathematical formulation of convolution neural networks
Convolutional Neural Networks (CNNs) Implementation
Available in
days
days
after you enroll
Machine Learning Project III - Identifying Objects with CNNs
Available in
days
days
after you enroll
Recurrent Neural Networks (RNNs) Theory
Available in
days
days
after you enroll
-
StartWhy do recurrent neural networks are important? (4:30)
-
StartRecurrent neural networks basics (8:58)
-
StartVanishing and exploding gradients problem (9:22)
-
StartLong-short term memory (LSTM) model (10:55)
-
StartGated recurrent units (GRUs) (3:23)
-
StartMathematical formulation of recurrent neural networks
Recurrent Neural Networks (RNNs) Implementation
Available in
days
days
after you enroll
Reinforcement Learning
Available in
days
days
after you enroll
Markov Decision Process (MDP) Theory
Available in
days
days
after you enroll
-
StartMarkov decision processes basics I (5:38)
-
StartMarkov decision processes basics II (6:21)
-
StartMarkov decision processes - equations (12:00)
-
StartMarkov decision processes - illustration (7:49)
-
StartBellman-equation (5:41)
-
StartHow to solve MDP problems? (2:20)
-
StartWhat is value iteration? (6:28)
-
StartWhat is policy iteration? (3:52)
-
StartMathematical formulation of reinforcement learning
Exploration vs. Exploitation Problem
Available in
days
days
after you enroll
Q Learning Theory
Available in
days
days
after you enroll
Q Learning Implementation (Tic Tac Toe)
Available in
days
days
after you enroll
-
StartTic tac toe with Q learning implementation I (3:45)
-
StartTic tac toe with Q learning implementation II (7:38)
-
StartTic tac toe with Q learning implementation III (7:26)
-
StartTic tac toe with Q learning implementation IV (7:27)
-
StartTic tac toe with Q learning implementation V (4:56)
-
StartTic tac toe with Q learning implementation VI (12:06)
-
StartTic tac toe with Q learning implementation VII (6:23)
-
StartTic tac toe with Q learning implementation VIII (6:39)
Deep Q Learning Theory
Available in
days
days
after you enroll
Deep Q Learning Implementation (Tic Tac Toe)
Available in
days
days
after you enroll
-
StartTic Tac Toe with deep Q learning implementation I (3:53)
-
StartTic Tac Toe with deep Q learning implementation II (6:27)
-
StartTic Tac Toe with deep Q learning implementation III (10:39)
-
StartTic Tac Toe with deep Q learning implementation IV (5:05)
-
StartTic Tac Toe with deep Q learning implementation V (4:43)
### COMPUTER VISION ###
Available in
days
days
after you enroll
History of Computer Vision
Available in
days
days
after you enroll
Handling Images and Pixels
Available in
days
days
after you enroll
-
StartImages and pixel intensities (5:13)
-
StartHandling pixel intensities I (6:18)
-
StartHandling pixel intensities II (5:16)
-
StartWhy convolution is so important in image processing? (12:07)
-
StartImage processing - blur operation (5:08)
-
StartImage processing - edge detection kernel (5:38)
-
StartImage processing - sharpen operation (3:43)
Computer Vision Project I - Lane Detection Problem (Self-Driving Cars)
Available in
days
days
after you enroll
-
StartLane detection - the problem (1:44)
-
StartLane detection - handling videos (5:36)
-
StartLane detection - first transformations (4:21)
-
StartWhat is Canny edge detection? (6:32)
-
StartGetting the useful region of the image - masking (13:20)
-
StartDetecting lines - what is Hough transformation? (10:30)
-
StartDrawing lines on video frames (9:05)
-
StartTesting lane detection algorithm (2:19)
Histogram of Oriented Gradients (HOG) Algorithm Theory
Available in
days
days
after you enroll
-
StartHistogram of oriented gradients basics (3:48)
-
StartHistogram of oriented gradients - gradient kernel (6:55)
-
StartHistogram of oriented gradients - magnitude and angle (7:42)
-
StartHistogram of oriented gradients - normalization (4:46)
-
StartHistogram of oriented gradients - big picture (3:14)
Histogram of Oriented Gradients (HOG) Implementation
Available in
days
days
after you enroll
Convolutional Neural Networks (CNNs) Based Approaches
Available in
days
days
after you enroll
You Only Look Once (YOLO) Algorithm Theory
Available in
days
days
after you enroll
-
StartWhat is the YOLO approach? (5:26)
-
StartYOLO algorithm - grid cells (6:45)
-
StartYOLO algorithm - intersection over union (9:02)
-
StartHow to train the YOLO algorithm? (7:21)
-
StartYOLO algorithm - loss function (4:53)
-
StartYOLO algorithm - non-max suppression (2:52)
-
StartWhy to use the so-called anchor boxes? (6:10)
You Only Look Once (YOLO) Algorithm Implementation
Available in
days
days
after you enroll
-
StartYOLO algorithm implementation I (6:15)
-
StartYOLO algorithm implementation II (9:08)
-
StartYOLO algorithm implementation III (8:45)
-
StartYOLO algorithm implementation IV (12:47)
-
StartYOLO algorithm implementation V (12:07)
-
StartYOLO algorithm implementation VI (1:47)
-
StartYOLO algorithm implementation VII (3:47)
Single-Shot MultiBox Detector (SSD) Theory
Available in
days
days
after you enroll
-
StartWhat is the SSD algorithm? (3:50)
-
StartBasic concept behind SSD algorithm (architecture) (7:17)
-
StartBounding boxes and anchor boxes (10:16)
-
StartFeature maps and convolution layers (4:40)
-
StartHard negative mining during training (2:22)
-
StartRegularization (data augmentation) and non-max suppression during training (2:14)
SSD Algorithm Implementation
Available in
days
days
after you enroll
Course Materials
Available in
days
days
after you enroll
Course Materials (DOWNLOADS)
Available in
days
days
after you enroll
Frequently Asked Questions
When does the course start and finish?
The course starts now and never ends! It is a completely self-paced online course - you decide when you start and when you finish.
How long do I have access to the course?
How does lifetime access sound? After enrolling, you have unlimited access to this course for as long as you like - across any and all devices you own.
What if I am unhappy with the course?
We would never want you to be unhappy! If you are unsatisfied with your purchase, contact us in the first 30 days and we will give you a full refund.
What are the requirements for taking your course?
We'll use Python as the programming language to implement the machine learning related algorithms. Check out the FREE Python programming course if needed.
off original price!
The coupon code you entered is expired or invalid, but the course is still available!