Course curriculum

    1. Motivation

    2. Introduction Course Materials

    3. What is Deep Learning?

    4. Deep Learning Libraries

    5. CPU vs GPU vs TPU

    6. Working Environments

    7. Colab

    8. Setting Up Working Environments

    9. Notebook

    10. Face Recognition

    11. Face Recognition Files

    12. How To Use Course Materials

    13. Working With Zip Files

    14. Colab & Drive Connection

    15. Application: Age Detection (Prediction)

    16. Application: Gender & Race & Emotion Detection

    17. Assignment: Age, Gender, Race, Emotion Detection from Files

    18. Assignment Solution

    19. Bonus: Deep Learning History

    1. Logistic Regression Course Materials

    2. Quick Introduction

    3. Logistic Regression

    4. Exercises

    5. Making Predictions

    6. Measuring Performance

    7. Exercises

    8. How to Minimize the Cost Function?

    9. Updating Weights

    10. Exercises

    11. Recap

    12. Application: Breast Cancer Classification I

    13. Application: Breast Cancer Classification II

    14. Application: Breast Cancer Classification III

    15. Assignment: Logistic Regression

    16. Assignment Solution: Logistic Regression

    17. Bonus: Türev Nedir?

    18. Bonus: Kısmi Türev Nedir?

    19. Bonus: Gradyan Nedir?

    20. Exercises

    1. Course Materials

    2. Introduction

    3. Chapter 1: Basic Concepts of Artificial Neural Network

    4. Artificial Neuron

    5. Neural Network

    6. Activation Functions

    7. Cost Functions

    8. Application: Basic Concepts

    9. Exercises

    10. Chapter 2: Learning Process in Artificial Neural Network

    11. Initialization of Weights and Biases

    12. Forward Propagation

    13. Calculation of the Loss Function

    14. Backpropagation

    15. Update Weights I

    16. Update Weights II

    17. Common Problems in Learning Process

    18. Application: Learning Process in ANN

    19. Exercises

    20. Chapter 3: Tensorflow & Keras

    21. Install Tensorflow and Keras

    22. Data Preparation

    23. Building the Model

    24. Training

    25. Tensor & Tensorflow Dataset

    26. Using Tensorflow Dataset

    27. Data Preparation Using Tensorflow Dataset

    28. Model Evaluation

    29. Assignment: Tensorflow Dataset & Modeling

    30. Assignment Solution: Tensorflow Dataset & Modeling

    31. Exercises

    32. Chapter 4: Enhancing Neural Network: Overfitting

    33. Train, Validation and Test Set

    34. Regularization

    35. Dropout

    36. Batch Normalization

    37. Early Stopping

    38. Data Augmentation

    39. Structured Data Modeling: Overview

    40. Structured Data Modeling I: Data Preparation

    41. Structured Data Modeling II: Modeling

    42. Structured Data Modeling III: Callbacks

    43. Structured Data Modeling IV: Training

    44. Structured Data Modeling V: Evaluation

    45. Structured Data Modeling VI: Loading Best Model

    46. Structured Data Modeling VII: Prediction

    47. Structured Data Modeling VIII: Hyperparameters

    48. Assignment: Checking the Overfitting

    49. Assignment Solution: Checking the Overfitting

    50. Exercises

    51. Chapter 5: Enhancing Neural Network: Hyperparameter Optimization

    52. Initialization Methods

    53. Application: Initialization Methods

    54. Layers, Units, Dropout

    55. Random Search

    56. Batch Size, Activation Functions, Learning Rate, Regularization

    57. All Together

    58. Final Model

    59. Assignment: Hyperparameter Optimization

    60. Assignment Solution: Hyperparameter Optimization

    61. Exercises

    62. Chapter 6: Bonus: Optimization Algorithms (Batch, Mini Batch, SGD)

    63. Bonus: Momentum

    64. Bonus: RMSprop

    65. Bonus: Adam

    66. Recap

    67. Case Study: Telco Churn Prediction

    68. Functions

    69. Data Preparation

    70. Base Model with Binary Log Loss

    71. Weighted Binary Log Loss

    72. Monitoring with AUC

    73. Hyperparameter Optimization

    74. Retrain All Dataset

    75. Prediction Lecture Materials

    76. Prediction I

    77. Prediction II

    78. Prediction III

    79. Case Study: House Price Prediction

    80. Data Preparation

    81. Modeling

    82. Inverse Prediction

    83. Hyperparameter Optimization

    84. Error Analysis I

    85. Error Analysis II

    86. Assignment Lecture Files

    87. Assignment: New Patients Prediction

    88. Assignment Solution: New Patients Prediction

    1. Course Materials

    2. Chapter 1: Motivation & Introduction

    3. Introduction

    4. Pixels

    5. Gray Scale Images

    6. Color Images

    7. Exercises

    8. Chapter 2: Basic Concepts & Learning Process

    9. Feature Extraction

    10. What is Convolution?

    11. Convolution Layers

    12. Pooling, Flatten, Fully Connected Layers

    13. Learning Process

    14. Cost Function (Softmax, Cross Entropi, MacroAUC, MicroAUC)

    15. Exercises

    16. Chapter 3: Application Image Classification With CNN

    17. Data Preparation

    18. Create Model

    19. Model Compile

    20. Model Training

    21. Assignment: Image Classification

    22. Assignment Solution: Image Classification

    23. Case Study: Garbage Classification

    24. Case Study: Data Understanding

    25. Case Study: Data Augmentation

    26. Case Study: Modeling

    27. Case Study: Model Performance

    28. Case Study: Prediction

    29. Exercises

    30. Chapter 4: CNN Architectures

    31. Model Sources

    32. Data Sets

    33. LeNet

    34. AlexNet

    35. VGG

    36. Application: VGG

    37. GoogleNet

    38. Application: Xception

    39. ResNet (Residual Network)

    40. Application: ResNet (Residual Network)

    41. Application: InceptionResNetV2

    42. More Models (MobileNet, DenseNet, EfficientNet)

    43. Application: MobileNet, DenseNet, EfficientNet

    44. Bonus: Compare All Models

    45. Bonus: PyTorch

    46. Assignment: Using Pretrained Model

    47. Assignment Solution: Using Pretrained Model

    48. Exercises

    49. Chapter 5: Transfer Learning and Fine Tuning

    50. Frozen Layers: MobileNet Backbone

    51. Layers

    52. Training

    53. Model Performance

    54. Prediction

    55. Full Network Fine Tuning

    56. Full Network Training

    57. Full Network Prediction

    58. Assignment: Fine Tuning

    59. Assignment Solution: Fine Tuning

    60. Exercises

    61. Chapter 6: Object Detection

    62. Sliding Window

    63. R-CNN

    64. Fast R-CNN

    65. Faster R-CNN

    66. Understanding the Object Detection Process: Data Structures

    67. Understanding the Object Detection Process: Training

    68. Understanding the Object Detection Process: Prediction

    69. Application: Faster R-CNN

    70. Prediction

    71. Detect Objects

    72. Mask R-CNN

    73. Application: Mask R-CNN

    74. SSD (Single Shot Multibox Detector)

    75. Application: SSD (Single Shot Multibox Detector)

    76. RetinaNet

    77. Application: RetinaNet

    78. YOLO (You Only Look Once)

    79. Application: YOLO v8

    80. Application: YOLO v3

    81. Application: Object Tracking with YOLO v3

    82. Application: Object Tracking with YOLO v8

    83. Application: Object Counting with YOLO v8

    84. Application: Real Time Object Detection

    85. Exercises

    1. Course Materials

    2. Chapter 1: Sequence Models and RNN

    3. What is Recurrent Neural Network?

    4. Basic Consepts of RNN

    5. Unfolded Graph

    6. How to Calculate Hidden State?

    7. Learning Process in RNN

    8. Long Term Dependencies

    9. Exercises

    10. Application: Weather Forecasting

    11. Data Preparation

    12. Time Series Visualisation

    13. Correlation HeatMap

    14. Anomaly Detection

    15. Time Based Splitting

    16. Scaling

    17. Time Window

    18. Model

    19. Model Performance

    20. Plot Predictions

    21. Chapter 2: Long Short-Term Memory (LSTM)

    22. Motivation

    23. Memory Cell

    24. Forget Gate

    25. Input Gate

    26. Output Gate

    27. Learning Process in LSTM

    28. Exercises

    29. Weather Forecasting with LSTM

    30. Weather Forecasting for All Data

    31. Hyperparameter Optimization

    32. Return Sequences

    33. Random Search

    34. Gated Recurrent Unit (GRU)

    35. Application: GRU

    36. Assignment: Weather Forecasting

    37. Assignment Solution: Weather Forecasting

    38. Chapter 3: Natural Language Processing (NLP)

    39. Mathematical Representations

    40. Bag of Words

    41. Word Embeddings

    42. Word2Vec & GloVe & FastText

    43. Download and Loading GloVe Vectors

    44. Cosine Similarity for Love & Hate

    45. Similarity Between Global Keywords and Countries

    46. King - Man + Woman = ?

    47. Exercises

    48. Emotion Classification I: Data Understanding

    49. Emotion Classification II: Text Preprocessing

    50. Emotion Classification III: Modeling with Keras Embeddings

    51. Emotion Classification IV: Play With Embeddings

    52. Emotion Classification V: 2D Visualization of Emotion Vectors

    53. Emotion Classification with GloVe & LSTM I: Data Preparation

    54. Emotion Classification with GloVe & LSTM II: Modeling

    55. Emotion Classification with GloVe & LSTM III: Play with Embeddings

    56. Emotion Classification with FastText & LSTM I: Modeling

    57. Emotion Classification with FastText & LSTM II: Prediction

    58. Assignment: Word Embeddings

    59. Assignment Solution: Word Embeddings

    60. Tebrikler!

About this course

  • 272 ders
  • 26 saat video içeriği