Deep Learning Topics

Explore our comprehensive collection of deep learning topics. Click on any topic to dive deeper.

01

Introduction to Deep Learning

What is Deep Learning?

DL vs ML vs AI – Key differences

Use-cases of DL

Biological Neuron vs Artificial Neuron

02

Perceptron and Neural Network Basics

Perceptron Model

Activation Functions

Multi-Layer Perceptron (MLP)

Forward and Backward Propagation

Loss Functions

03

Using TensorFlow / PyTorch / Keras

Tensors and computation graphs

Model definition, compiling, fitting, evaluating

04

Training Deep Models

Epochs, Batches, Learning Rate

Optimizers – SGD, Adam, RMSprop

Overfitting & Underfitting

Regularization – Dropout, L2

Batch Normalization

05

Convolutional Neural Networks (CNNs)

CNN Layers: Conv, Pooling, Flatten

Use-case: Image Classification

06

Advanced CNN Architectures

VGG, ResNet, Inception, MobileNet

Use-case: Efficient image classification

Concept: Skip connections, depth, bottlenecks

07

Transfer Learning & Fine-tuning

Pre-trained models: VGG, ResNet, etc.

Freezing layers, adding custom layers

08

Autoencoders & Anomaly Detection

Architecture of autoencoders

Use-case: Noise removal, compression, outlier detection

09

Generative Adversarial Networks (GANs)

Generator vs Discriminator

DCGAN basics

Use-case: Image generation, super-resolution

10

Model Evaluation & Explainability

Metrics: Accuracy, Precision, Recall, F1, AUC

Confusion Matrix

Model Explainability: Grad-CAM, Feature Maps

11

Model Deployment

Save/load models

Flask / Streamlit for web deployment

ONNX / TensorFlow Lite for edge deployment