How rupakraj/deeplearning works
DeepLearning is a classroom collection of runnable Jupyter lessons, not a single application pipeline. The principal workflow is for a learner to open a topic notebook, select a Python/Jupyter kernel, and run cells to explore its demonstrations. The graph groups the documented lessons by subject and includes the separate representation-learning collection and its synthetic CRM-data generator. Lesson capabilities come from the README; notebook internals were not sampled, so no connections between lessons or to datasets are inferred.
Main entry points: make_crm.py Synthetic CRM Generator · pytorch_toy_example.ipynb PyTorch Toy Example · overfit_underfit_regularization.ipynb Regularization · limitation_of_gradient.ipynb Gradient Descent Limits
Components 19
Foundations & Optimization
- PyTorch Toy Example
pytorch_toy_example.ipynb - Regularization
overfit_underfit_regularization.ipynb - Gradient Descent Limits
limitation_of_gradient.ipynb - Adaptive Learning Rates
adaptive_learning_rates.ipynb
Computer Vision
- CNN Motivation
need_for_cnn.ipynb - AlexNet Classification
alexnet_image_classification.ipynb - Batch Normalization
batch_normalization.ipynb
Representation Learning
- Autoencoder Representations
autoencoder_representation_learning.ipynb - Word2Vec Representations
word2vec_autoencoder.ipynb - Representation Dataset Prep
rep-learning/01_dataset_preparation.ipynb - Representation Model Training
rep-learning/02_model_and_training.ipynb
Language & Retrieval
- Embedding Retrieval
embedding_retrieval.ipynb - Sequence Models
need_for_sequence_models.ipynb - Neural N-Gram Model
neural_ngram_language_model.ipynb - Embedding Building
rep-learning/building_embedding.ipynb
CRM Data
- Synthetic CRM Generator
rep-learning/scripts/make_crm.py - CRM Dataset
rep-learning/data/crm.csv
Other components
- Learner
- Jupyter / Python Runtime
Connections 13
- Learner → PyTorch Toy Example: opens and runs
readme.md - Learner → Regularization: opens and runs
readme.md - Learner → Gradient Descent Limits: opens and runs
readme.md - Learner → Adaptive Learning Rates: opens and runs
readme.md - Learner → CNN Motivation: opens and runs
readme.md - Learner → AlexNet Classification: opens and runs
readme.md - Learner → Batch Normalization: opens and runs
readme.md - Learner → Autoencoder Representations: opens and runs
readme.md - Learner → Word2Vec Representations: opens and runs
readme.md - Learner → Embedding Retrieval: opens and runs
readme.md - Learner → Sequence Models: opens and runs
readme.md - Learner → Neural N-Gram Model: opens and runs
readme.md - Synthetic CRM Generator → CRM Dataset: writes CSV
rep-learning/scripts/make_crm.py