Course curriculum
-
-
Motivation
-
Introduction Course Materials
-
What is Deep Learning?
-
Deep Learning Libraries
-
CPU vs GPU vs TPU
-
Working Environments
-
Colab
-
Setting Up Working Environments
-
Notebook
-
Face Recognition
-
Face Recognition Files
-
How To Use Course Materials
-
Working With Zip Files
-
Colab & Drive Connection
-
Application: Age Detection (Prediction)
-
Application: Gender & Race & Emotion Detection
-
Assignment: Age, Gender, Race, Emotion Detection from Files
-
Assignment Solution
-
Bonus: Deep Learning History
-
-
-
Logistic Regression Course Materials
-
Quick Introduction
-
Logistic Regression
-
Exercises
-
Making Predictions
-
Measuring Performance
-
Exercises
-
How to Minimize the Cost Function?
-
Updating Weights
-
Exercises
-
Recap
-
Application: Breast Cancer Classification I
-
Application: Breast Cancer Classification II
-
Application: Breast Cancer Classification III
-
Assignment: Logistic Regression
-
Assignment Solution: Logistic Regression
-
Bonus: Türev Nedir?
-
Bonus: Kısmi Türev Nedir?
-
Bonus: Gradyan Nedir?
-
Exercises
-
-
-
Course Materials
-
Introduction
-
Chapter 1: Basic Concepts of Artificial Neural Network
-
Artificial Neuron
-
Neural Network
-
Activation Functions
-
Cost Functions
-
Application: Basic Concepts
-
Exercises
-
Chapter 2: Learning Process in Artificial Neural Network
-
Initialization of Weights and Biases
-
Forward Propagation
-
Calculation of the Loss Function
-
Backpropagation
-
Update Weights I
-
Update Weights II
-
Common Problems in Learning Process
-
Application: Learning Process in ANN
-
Exercises
-
Chapter 3: Tensorflow & Keras
-
Install Tensorflow and Keras
-
Data Preparation
-
Building the Model
-
Training
-
Tensor & Tensorflow Dataset
-
Using Tensorflow Dataset
-
Data Preparation Using Tensorflow Dataset
-
Model Evaluation
-
Assignment: Tensorflow Dataset & Modeling
-
Assignment Solution: Tensorflow Dataset & Modeling
-
Exercises
-
Chapter 4: Enhancing Neural Network: Overfitting
-
Train, Validation and Test Set
-
Regularization
-
Dropout
-
Batch Normalization
-
Early Stopping
-
Data Augmentation
-
Structured Data Modeling: Overview
-
Structured Data Modeling I: Data Preparation
-
Structured Data Modeling II: Modeling
-
Structured Data Modeling III: Callbacks
-
Structured Data Modeling IV: Training
-
Structured Data Modeling V: Evaluation
-
Structured Data Modeling VI: Loading Best Model
-
Structured Data Modeling VII: Prediction
-
Structured Data Modeling VIII: Hyperparameters
-
Assignment: Checking the Overfitting
-
Assignment Solution: Checking the Overfitting
-
Exercises
-
Chapter 5: Enhancing Neural Network: Hyperparameter Optimization
-
Initialization Methods
-
Application: Initialization Methods
-
Layers, Units, Dropout
-
Random Search
-
Batch Size, Activation Functions, Learning Rate, Regularization
-
All Together
-
Final Model
-
Assignment: Hyperparameter Optimization
-
Assignment Solution: Hyperparameter Optimization
-
Exercises
-
Chapter 6: Bonus: Optimization Algorithms (Batch, Mini Batch, SGD)
-
Bonus: Momentum
-
Bonus: RMSprop
-
Bonus: Adam
-
Recap
-
Case Study: Telco Churn Prediction
-
Functions
-
Data Preparation
-
Base Model with Binary Log Loss
-
Weighted Binary Log Loss
-
Monitoring with AUC
-
Hyperparameter Optimization
-
Retrain All Dataset
-
Prediction Lecture Materials
-
Prediction I
-
Prediction II
-
Prediction III
-
Case Study: House Price Prediction
-
Data Preparation
-
Modeling
-
Inverse Prediction
-
Hyperparameter Optimization
-
Error Analysis I
-
Error Analysis II
-
Assignment Lecture Files
-
Assignment: New Patients Prediction
-
Assignment Solution: New Patients Prediction
-
-
-
Course Materials
-
Chapter 1: Motivation & Introduction
-
Introduction
-
Pixels
-
Gray Scale Images
-
Color Images
-
Exercises
-
Chapter 2: Basic Concepts & Learning Process
-
Feature Extraction
-
What is Convolution?
-
Convolution Layers
-
Pooling, Flatten, Fully Connected Layers
-
Learning Process
-
Cost Function (Softmax, Cross Entropi, MacroAUC, MicroAUC)
-
Exercises
-
Chapter 3: Application Image Classification With CNN
-
Data Preparation
-
Create Model
-
Model Compile
-
Model Training
-
Assignment: Image Classification
-
Assignment Solution: Image Classification
-
Case Study: Garbage Classification
-
Case Study: Data Understanding
-
Case Study: Data Augmentation
-
Case Study: Modeling
-
Case Study: Model Performance
-
Case Study: Prediction
-
Exercises
-
Chapter 4: CNN Architectures
-
Model Sources
-
Data Sets
-
LeNet
-
AlexNet
-
VGG
-
Application: VGG
-
GoogleNet
-
Application: Xception
-
ResNet (Residual Network)
-
Application: ResNet (Residual Network)
-
Application: InceptionResNetV2
-
More Models (MobileNet, DenseNet, EfficientNet)
-
Application: MobileNet, DenseNet, EfficientNet
-
Bonus: Compare All Models
-
Bonus: PyTorch
-
Assignment: Using Pretrained Model
-
Assignment Solution: Using Pretrained Model
-
Exercises
-
Chapter 5: Transfer Learning and Fine Tuning
-
Frozen Layers: MobileNet Backbone
-
Layers
-
Training
-
Model Performance
-
Prediction
-
Full Network Fine Tuning
-
Full Network Training
-
Full Network Prediction
-
Assignment: Fine Tuning
-
Assignment Solution: Fine Tuning
-
Exercises
-
Chapter 6: Object Detection
-
Sliding Window
-
R-CNN
-
Fast R-CNN
-
Faster R-CNN
-
Understanding the Object Detection Process: Data Structures
-
Understanding the Object Detection Process: Training
-
Understanding the Object Detection Process: Prediction
-
Application: Faster R-CNN
-
Prediction
-
Detect Objects
-
Mask R-CNN
-
Application: Mask R-CNN
-
SSD (Single Shot Multibox Detector)
-
Application: SSD (Single Shot Multibox Detector)
-
RetinaNet
-
Application: RetinaNet
-
YOLO (You Only Look Once)
-
Application: YOLO v8
-
Application: YOLO v3
-
Application: Object Tracking with YOLO v3
-
Application: Object Tracking with YOLO v8
-
Application: Object Counting with YOLO v8
-
Application: Real Time Object Detection
-
Exercises
-
-
-
Course Materials
-
Chapter 1: Sequence Models and RNN
-
What is Recurrent Neural Network?
-
Basic Consepts of RNN
-
Unfolded Graph
-
How to Calculate Hidden State?
-
Learning Process in RNN
-
Long Term Dependencies
-
Exercises
-
Application: Weather Forecasting
-
Data Preparation
-
Time Series Visualisation
-
Correlation HeatMap
-
Anomaly Detection
-
Time Based Splitting
-
Scaling
-
Time Window
-
Model
-
Model Performance
-
Plot Predictions
-
Chapter 2: Long Short-Term Memory (LSTM)
-
Motivation
-
Memory Cell
-
Forget Gate
-
Input Gate
-
Output Gate
-
Learning Process in LSTM
-
Exercises
-
Weather Forecasting with LSTM
-
Weather Forecasting for All Data
-
Hyperparameter Optimization
-
Return Sequences
-
Random Search
-
Gated Recurrent Unit (GRU)
-
Application: GRU
-
Assignment: Weather Forecasting
-
Assignment Solution: Weather Forecasting
-
Chapter 3: Natural Language Processing (NLP)
-
Mathematical Representations
-
Bag of Words
-
Word Embeddings
-
Word2Vec & GloVe & FastText
-
Download and Loading GloVe Vectors
-
Cosine Similarity for Love & Hate
-
Similarity Between Global Keywords and Countries
-
King - Man + Woman = ?
-
Exercises
-
Emotion Classification I: Data Understanding
-
Emotion Classification II: Text Preprocessing
-
Emotion Classification III: Modeling with Keras Embeddings
-
Emotion Classification IV: Play With Embeddings
-
Emotion Classification V: 2D Visualization of Emotion Vectors
-
Emotion Classification with GloVe & LSTM I: Data Preparation
-
Emotion Classification with GloVe & LSTM II: Modeling
-
Emotion Classification with GloVe & LSTM III: Play with Embeddings
-
Emotion Classification with FastText & LSTM I: Modeling
-
Emotion Classification with FastText & LSTM II: Prediction
-
Assignment: Word Embeddings
-
Assignment Solution: Word Embeddings
-
Tebrikler!
-
About this course
- 272 ders
- 26 saat video içeriği