Deep Learning 🧠

My solutions and notes for Deep Learning Specialization by Stanford (DeepLearning.ai)

1. NNs and Deep Learning

• Logistic Regression
• Single Hidden Layer Neural Net
• Deep Neural Net

2. Improving Deep NNs

• Regularization
• Initialization
• Gradient Checking
• Optimization (Mini-batch, RMSProps, GD with Momentum, Adam)
• Batch Norm (Andrej Karpathy's Video)
• Hyperparameters Tuning
• Tensorflow

3. Structuring ML Projects

• Orthogonalization
• Single Number Evaluation
• Satisfying and Optimizing Metric
• Train/Dev/Test Distributions
• Human Level Performance
• Avoidable Bias
• Error Analysis
• Mismatched Training and Dev/Test Sets
• Transfer Learning
• Multitask Learning
• End-to-end Deep Learning

4. Convolutional Neural Nets

• Edge Detection
• Padding
• Pooling
• CNN (from scratch)
• CNN (using Keras Sequential + Functional API)
• ResNets
• MobileNet
• Efficient Net
• Object Localization
• Image Segmentation

5. Sequence Models

• RNN
• GNU
• LSTM
• Word Embeddings
• GloVe
• Negative Sampling
• Attention Model
• Audio Dataset
• Trigger Word Detection
• Transformers

Specialization Certificate