• Lesson 1: What is TensorFlow?
• Lesson 2: History and Evolution of TensorFlow
• Lesson 3: Installing TensorFlow (Windows, macOS, Linux)
• Lesson 4: Importing and Using TensorFlow
• Lesson 5: TensorFlow vs Other Deep Learning Frameworks

• Lesson 1: Understanding Tensors in TensorFlow
• Lesson 2: Creating and Manipulating Tensors
• Lesson 3: Tensor Data Types and Shapes
• Lesson 4: Indexing and Slicing Tensors
• Lesson 5: Broadcasting and Element-wise Operations

• Lesson 1: Understanding TensorFlow Computational Graphs
• Lesson 2: Working with TensorFlow Constants and Variables
• Lesson 3: Basic Mathematical Operations in TensorFlow
• Lesson 4: Using TensorFlow Functions for Linear Algebra
• Lesson 5: Executing Computations with tf.function

• Lesson 1: Eager Execution vs Graph Execution
• Lesson 2: Using tf.function for Performance Optimization
• Lesson 3: Debugging TensorFlow Computations
• Lesson 4: Managing Resources with tf.device
• Lesson 5: Understanding Autograph in TensorFlow

• Lesson 1: Introduction to tf.data API
• Lesson 2: Loading Data from CSV, JSON, and TXT Files
• Lesson 3: Working with Datasets and Iterators
• Lesson 4: Data Augmentation and Preprocessing
• Lesson 5: Shuffling, Batching, and Prefetching Data

• Lesson 1: Converting NumPy Arrays to Tensors
• Lesson 2: Converting Tensors to NumPy Arrays
• Lesson 3: Performance Comparison: NumPy vs TensorFlow
• Lesson 4: Hybrid Operations Between NumPy and TensorFlow
• Lesson 5: TensorFlow’s Special NumPy-like Operations

• Lesson 1: Introduction to Deep Learning
• Lesson 2: Basics of Neural Networks and Activation Functions
• Lesson 3: Creating a Simple Neural Network in TensorFlow
• Lesson 4: Understanding Model Training and Loss Functions
• Lesson 5: Introduction to Backpropagation

• Lesson 1: Introduction to TensorFlow’s Keras API
• Lesson 2: Defining a Sequential Model
• Lesson 3: Adding Layers to a Model
• Lesson 4: Compiling a Model with Optimizers and Losses
• Lesson 5: Training and Evaluating Models

• Lesson 1: Introduction to Model Persistence
• Lesson 2: Saving Models with tf.keras.models.save_model
• Lesson 3: Loading Pre-trained Models
• Lesson 4: Saving Model Weights Only
• Lesson 5: TensorFlow Hub for Pre-trained Models

• Lesson 1: Overview of Gradient Descent and Optimizers
• Lesson 2: Stochastic Gradient Descent (SGD)
• Lesson 3: Adam, RMSprop, and Adagrad Optimizers
• Lesson 4: Customizing Loss Functions
• Lesson 5: Implementing Custom Training Loops

• Lesson 1: Introduction to Image Processing with TensorFlow
• Lesson 2: Loading Images with tf.keras.preprocessing
• Lesson 3: Performing Image Augmentation
• Lesson 4: Using Pre-trained CNNs for Feature Extraction
• Lesson 5: Training a CNN for Image Classification

• Lesson 1: Working with Text Data in TensorFlow
• Lesson 2: Tokenization and Word Embeddings
• Lesson 3: Creating Text Classification Models
• Lesson 4: Recurrent Neural Networks (RNNs) Basics
• Lesson 5: Introduction to Transformers in TensorFlow

• Lesson 1: Broadcasting and Advanced Arithmetic Operations
• Lesson 2: Working with Sparse Tensors
• Lesson 3: Using Ragged Tensors for Variable-Length Data
• Lesson 4: Custom Operations with tf.raw_ops
• Lesson 5: Efficient Computation with tf.TensorArray

• Lesson 1: Building Custom Layers in Keras
• Lesson 2: Implementing Custom Training Loops
• Lesson 3: Creating Custom Loss Functions
• Lesson 4: Using Custom Metrics for Evaluation
• Lesson 5: Debugging Custom TensorFlow Models

• Lesson 1: What is Transfer Learning?
• Lesson 2: Using Pre-trained Models with TensorFlow Hub
• Lesson 3: Freezing and Unfreezing Layers
• Lesson 4: Fine-Tuning a Model for New Tasks
• Lesson 5: Best Practices for Transfer Learning

• Lesson 1: Introduction to NLP in TensorFlow
• Lesson 2: Implementing Word Embeddings with tf.keras.layers.Embedding
• Lesson 3: Building an LSTM-based Text Classifier
• Lesson 4: Transformer Models in TensorFlow
• Lesson 5: Using TensorFlow for Text Generation

• Lesson 1: Using Convolutional Neural Networks (CNNs)
• Lesson 2: Implementing Object Detection with TensorFlow
• Lesson 3: Image Segmentation with U-Net
• Lesson 4: Style Transfer with TensorFlow
• Lesson 5: Working with TensorFlow Lite for Mobile Deployment

• Lesson 1: Introduction to Reinforcement Learning (RL)
• Lesson 2: Implementing Q-learning in TensorFlow
• Lesson 3: Policy Gradients with TensorFlow
• Lesson 4: Deep Q Networks (DQN) in TensorFlow
• Lesson 5: Using TensorFlow with OpenAI Gym

• Lesson 1: Introduction to TensorFlow Extended (TFX)
• Lesson 2: Creating Data Pipelines with TFX
• Lesson 3: Model Analysis and Validation
• Lesson 4: Deploying Models with TensorFlow Serving
• Lesson 5: TensorFlow Model Monitoring in Production

• Lesson 1: Using tf.distribute.Strategy for Multi-GPU Training
• Lesson 2: Data Parallelism vs Model Parallelism
• Lesson 3: Training on TPU with TensorFlow
• Lesson 4: Distributed Training with Horovod
• Lesson 5: Performance Optimization for Large Models

• Lesson 1: Deploying TensorFlow Models on Edge Devices
• Lesson 2: Working with TensorFlow Lite for Mobile Apps
• Lesson 3: Quantization and Model Optimization
• Lesson 4: Using TensorFlow.js for Web Deployment
• Lesson 5: Running TensorFlow on Microcontrollers

• Lesson 1: Introduction to Generative Models
• Lesson 2: Implementing Variational Autoencoders (VAEs)
• Lesson 3: Generative Adversarial Networks (GANs) in TensorFlow
• Lesson 4: Diffusion Models for Image Generation
• Lesson 5: Using TensorFlow for AI Art Generation

Course Duration: about 50+10 hours

The online class is held via Skype (or Zoom or Microsoft Teams) and the cost per hour of tutoring is only $15. At the end of this long course, you will master all the required basic and advanced concepts of TensorFlow Library and we will accomplish a real-world project together for about 10 hours, which fully prepares you to find a job as a entry level AI / ML programmer in AI / ML job markets.
To book this class, message or call my telegram or WhatsApp:
+98 (912) 490-8372 or +98 (935) 490-8372.
You can also send email to me:
abolfazl.mohammadijoo@gmail.com