Python for AI

4.

Deep Learning Frameworks

4.1.

Deep Learning Fundamentals

4.1.1.

Neural Network Architecture

4.1.1.1.

4.1.1.2.

Multi-layer Perceptrons

4.1.1.3.

Deep Neural Networks

4.1.1.4.

Network Topology

4.1.2.

Neural Network Components

4.1.2.1.

Neurons and Nodes

4.1.2.2.

4.1.2.2.1.

4.1.2.2.2.

4.1.2.2.3.

4.1.2.3.

Weights and Biases

4.1.2.4.

4.1.3.

Activation Functions

4.1.3.1.

Linear Activation

4.1.3.2.

Sigmoid Function

4.1.3.3.

Hyperbolic Tangent

4.1.3.4.

4.1.3.5.

4.1.3.6.

4.1.3.7.

4.1.3.8.

Softmax Function

4.1.4.

4.1.4.1.

Mean Squared Error

4.1.4.2.

Mean Absolute Error

4.1.4.3.

Binary Cross-Entropy

4.1.4.4.

Categorical Cross-Entropy

4.1.4.5.

Sparse Categorical Cross-Entropy

4.1.4.6.

4.1.4.7.

Custom Loss Functions

4.1.5.

Optimization Algorithms

4.1.5.1.

Gradient Descent

4.1.5.2.

Stochastic Gradient Descent

4.1.5.3.

Mini-batch Gradient Descent

4.1.5.4.

4.1.5.5.

4.1.5.6.

4.1.5.7.

4.1.5.8.

4.1.5.9.

Learning Rate Scheduling

4.1.6.

Backpropagation

4.1.6.1.

4.1.6.2.

4.1.6.3.

Chain Rule Application

4.1.6.4.

Gradient Computation

4.1.6.5.

4.1.7.

Regularization Techniques

4.1.7.1.

L1 Regularization

4.1.7.2.

L2 Regularization

4.1.7.3.

4.1.7.4.

Batch Normalization

4.1.7.5.

Layer Normalization

4.1.7.6.

4.2.

TensorFlow and Keras

4.2.1.

TensorFlow Basics

4.2.1.1.

TensorFlow Architecture

4.2.1.2.

Computational Graphs

4.2.1.3.

Sessions and Eager Execution

4.2.1.4.

TensorFlow 2.x Features

4.2.2.

Tensors in TensorFlow

4.2.2.1.

Tensor Creation

4.2.2.2.

Tensor Properties

4.2.2.3.

Tensor Operations

4.2.2.4.

Tensor Manipulation

4.2.2.5.

4.2.3.

Keras High-level API

4.2.3.1.

Keras Integration with TensorFlow

4.2.3.2.

Model Building Approaches

4.2.3.3.

4.2.4.

Building Models

4.2.4.1.

4.2.4.1.1.

Creating Sequential Models

4.2.4.1.2.

4.2.4.1.3.

Model Configuration

4.2.4.2.

4.2.4.2.1.

Input and Output Layers

4.2.4.2.2.

Complex Architectures

4.2.4.2.3.

Multi-input Models

4.2.4.2.4.

Multi-output Models

4.2.4.2.5.

4.2.4.3.

Subclassing API

4.2.4.3.1.

Custom Model Classes

4.2.4.3.2.

4.2.5.

Model Compilation

4.2.5.1.

Optimizer Selection

4.2.5.2.

Loss Function Selection

4.2.5.3.

Metrics Configuration

4.2.5.4.

Compilation Parameters

4.2.6.

4.2.6.1.

Training Data Preparation

4.2.6.2.

4.2.6.3.

Batch Size Selection

4.2.6.4.

Epochs Configuration

4.2.6.5.

Validation Data

4.2.7.

Model Evaluation

4.2.7.1.

Evaluation Metrics

4.2.7.2.

Model Performance Assessment

4.2.7.3.

Prediction Generation

4.2.8.

4.2.8.1.

4.2.8.2.

ModelCheckpoint

4.2.8.3.

ReduceLROnPlateau

4.2.8.4.

4.2.8.5.

Custom Callbacks

4.2.9.

Model Persistence

4.2.9.1.

4.2.9.2.

4.2.9.3.

4.2.9.4.

Checkpoint Management

4.2.10.

Advanced TensorFlow Features

4.2.10.1.

Custom Training Loops

4.2.10.2.

4.2.10.3.

tf.function Decorator

4.2.10.4.

4.2.10.5.

Distributed Training

4.3.

4.3.1.

PyTorch Fundamentals

4.3.1.1.

PyTorch Philosophy

4.3.1.2.

Dynamic Computation Graphs

4.3.1.3.

Pythonic Design

4.3.2.

Tensors in PyTorch

4.3.2.1.

Tensor Creation

4.3.2.2.

Tensor Operations

4.3.2.3.

GPU Acceleration

4.3.2.4.

Tensor Manipulation

4.3.2.5.

Autograd System

4.3.3.

Automatic Differentiation

4.3.3.1.

Gradient Computation

4.3.3.2.

4.3.3.3.

Gradient Accumulation

4.3.3.4.

Gradient Clipping

4.3.4.

Neural Network Modules

4.3.4.1.

nn.Module Class

4.3.4.2.

Layer Definitions

4.3.4.3.

Parameter Management

4.3.4.4.

Module Composition

4.3.5.

Building Models

4.3.5.1.

Sequential Models

4.3.5.2.

Custom Model Classes

4.3.5.3.

Forward Method Implementation

4.3.5.4.

Model Architecture Design

4.3.6.

4.3.6.1.

Built-in Loss Functions

4.3.6.2.

Custom Loss Functions

4.3.6.3.

Loss Computation

4.3.7.

4.3.7.1.

4.3.7.2.

4.3.7.3.

Optimizer Configuration

4.3.7.4.

Learning Rate Scheduling

4.3.8.

4.3.8.1.

Dataset Classes

4.3.8.2.

4.3.8.3.

Data Transformations

4.3.8.4.

Batch Processing

4.3.9.

Training Loop Implementation

4.3.9.1.

4.3.9.2.

Evaluation Mode

4.3.9.3.

4.3.9.4.

Loss Calculation

4.3.9.5.

4.3.9.6.

Parameter Updates

4.3.10.

Model Evaluation

4.3.10.1.

4.3.10.2.

Performance Metrics

4.3.10.3.

4.3.11.

Model Persistence

4.3.11.1.

State Dictionary

4.3.11.2.

4.3.11.3.

4.3.11.4.

Checkpoint Management

4.3.12.

Advanced PyTorch Features

4.3.12.1.

Custom Datasets

4.3.12.2.

Data Augmentation

4.3.12.3.

Transfer Learning

4.3.12.4.

Model Deployment

Previous

3. Machine Learning with Scikit-Learn

Go to top

Next

5. Specialized AI Applications