# kartikgupta98/dl-worksheets architecture

> Architecture diagram of the GitHub repository kartikgupta98/dl-worksheets, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-09-30). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/kartikgupta98/dl-worksheets
- Repository: https://github.com/kartikgupta98/dl-worksheets

## Overview

This repository is a deep-learning teaching site: learners open self-contained browser worksheets to explore concepts through explanations, exercises, quizzes, and interactive demonstrations. A separate fraud-competition branch supplies Kaggle learning materials and tooling: it generates synthetic transaction data, calibrates modeling configurations, exports competition files, and provides student and instructor notebooks and technique cards. The README documents the worksheet topics and competition handouts; source excerpts show the competition tooling’s main calls. Individual worksheet internals were not sampled, so their links describe the documented learner workflow rather than inspected code behavior.

Main entry points: [`index.html`](https://github.com/kartikgupta98/dl-worksheets/blob/main/index.html) (Worksheet index), [`fraud_competition/calibrate.py`](https://github.com/kartikgupta98/dl-worksheets/blob/main/fraud_competition/calibrate.py) (Calibration runner), [`fraud_competition/exp2.py`](https://github.com/kartikgupta98/dl-worksheets/blob/main/fraud_competition/exp2.py) (Experiment configurations), [`fraud_competition/pipeline.py`](https://github.com/kartikgupta98/dl-worksheets/blob/main/fraud_competition/pipeline.py) (Modeling pipeline)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_worksheets["Deep-learning worksheets"]
  node_site_index["Worksheet index<br/>[index.html]"]
  node_activations["Activations<br/>[activations.html]"]
  node_backprop["Output-layer backprop"]
  node_gradient["Gradient descent"]
  node_momentum["Momentum and NAG"]
  node_adaptive_lr["Adaptive learning rates"]
  node_regularisation["Regularisation lab"]
  node_cnn["CNN worksheet"]
  node_architectures["CNN architectures"]
  node_inception_resnet["Inception and ResNet"]
end

subgraph group_competition_materials["Competition learning materials"]
  node_cards["Technique cards<br/>[technique_cards.md]"]
  node_starter_notebook["Student notebook"]
  node_instructor_materials["Instructor materials"]
end

subgraph group_competition_data["Data and calibration"]
  node_generator["Synthetic data generator<br/>[generate_data.py]"]
  node_experiment_configs["Experiment configurations<br/>[exp2.py]"]
  node_training_pipeline["Modeling pipeline<br/>[pipeline.py]"]
  node_calibration["Calibration runner<br/>[calibrate.py]"]
  node_experiment_summary["Experiment summary<br/>[summary.py]"]
end

subgraph group_competition_tools["Competition tooling"]
  node_kaggle_export["Kaggle export and scoring<br/>[export_kaggle.py]"]
  node_notebook_builder["Notebook builder<br/>[make_notebooks.py]"]
  node_card_renderer["Card-page renderer<br/>[make_cards_html.py]"]
  node_card_code_builder["Card-code notebook builder"]
end

node_learner(("Learner"))

node_learner -->|"opens"| node_site_index
node_site_index -->|"links to"| node_activations
node_site_index -->|"links to"| node_backprop
node_site_index -->|"links to"| node_gradient
node_site_index -->|"links to"| node_momentum
node_site_index -->|"links to"| node_adaptive_lr
node_site_index -->|"links to"| node_regularisation
node_site_index -->|"links to"| node_cnn
node_site_index -->|"links to"| node_architectures
node_site_index -->|"links to"| node_inception_resnet
node_calibration -->|"generates data"| node_generator
node_calibration -->|"loads configs"| node_experiment_configs
node_calibration -->|"runs models"| node_training_pipeline
node_experiment_configs -->|"imports defaults"| node_training_pipeline
node_experiment_summary -->|"uses summary"| node_calibration
node_kaggle_export -->|"uses settings"| node_experiment_configs
node_kaggle_export -->|"generates data"| node_generator
node_kaggle_export -->|"trains reference"| node_training_pipeline
node_notebook_builder -->|"uses pipeline"| node_training_pipeline
node_notebook_builder -->|"uses configs"| node_experiment_configs
node_card_renderer -->|"renders cards"| node_cards
node_card_code_builder -->|"uses card parser"| node_card_renderer
node_card_code_builder -->|"uses notebook builder"| node_notebook_builder

click node_site_index "https://github.com/kartikgupta98/dl-worksheets/blob/main/index.html"
click node_activations "https://github.com/kartikgupta98/dl-worksheets/blob/main/activations.html"
click node_backprop "https://github.com/kartikgupta98/dl-worksheets/blob/main/backprop_worksheet_output_layer.html"
click node_gradient "https://github.com/kartikgupta98/dl-worksheets/blob/main/lecture06_gradient_descent.html"
click node_momentum "https://github.com/kartikgupta98/dl-worksheets/blob/main/worksheet07_momentum_nag.html"
click node_adaptive_lr "https://github.com/kartikgupta98/dl-worksheets/blob/main/worksheet08_adaptive_lr.html"
click node_regularisation "https://github.com/kartikgupta98/dl-worksheets/blob/main/worksheet09_regularisation.html"
click node_cnn "https://github.com/kartikgupta98/dl-worksheets/blob/main/worksheet09_cnn.html"
click node_architectures "https://github.com/kartikgupta98/dl-worksheets/blob/main/worksheet10_architectures.html"
click node_inception_resnet "https://github.com/kartikgupta98/dl-worksheets/blob/main/worksheet11_inception_resnet.html"
click node_cards "https://github.com/kartikgupta98/dl-worksheets/blob/main/fraud_competition/materials/technique_cards.md"
click node_starter_notebook "https://github.com/kartikgupta98/dl-worksheets/blob/main/fraud_competition/materials/starter_notebook.ipynb"
click node_instructor_materials "https://github.com/kartikgupta98/dl-worksheets/blob/main/fraud_competition/materials/instructor_guide.md"
click node_generator "https://github.com/kartikgupta98/dl-worksheets/blob/main/fraud_competition/generate_data.py"
click node_experiment_configs "https://github.com/kartikgupta98/dl-worksheets/blob/main/fraud_competition/exp2.py"
click node_training_pipeline "https://github.com/kartikgupta98/dl-worksheets/blob/main/fraud_competition/pipeline.py"
click node_calibration "https://github.com/kartikgupta98/dl-worksheets/blob/main/fraud_competition/calibrate.py"
click node_experiment_summary "https://github.com/kartikgupta98/dl-worksheets/blob/main/fraud_competition/summary.py"
click node_kaggle_export "https://github.com/kartikgupta98/dl-worksheets/blob/main/fraud_competition/export_kaggle.py"
click node_notebook_builder "https://github.com/kartikgupta98/dl-worksheets/blob/main/fraud_competition/make_notebooks.py"
click node_card_renderer "https://github.com/kartikgupta98/dl-worksheets/blob/main/fraud_competition/make_cards_html.py"
click node_card_code_builder "https://github.com/kartikgupta98/dl-worksheets/blob/main/fraud_competition/make_card_code_notebook.py"

classDef toneNeutral fill:#f8fafc,stroke:#334155,stroke-width:1.5px,color:#0f172a
classDef toneBlue fill:#dbeafe,stroke:#2563eb,stroke-width:1.5px,color:#172554
classDef toneAmber fill:#fef3c7,stroke:#d97706,stroke-width:1.5px,color:#78350f
classDef toneMint fill:#dcfce7,stroke:#16a34a,stroke-width:1.5px,color:#14532d
classDef toneRose fill:#ffe4e6,stroke:#e11d48,stroke-width:1.5px,color:#881337
classDef toneIndigo fill:#e0e7ff,stroke:#4f46e5,stroke-width:1.5px,color:#312e81
classDef toneTeal fill:#ccfbf1,stroke:#0f766e,stroke-width:1.5px,color:#134e4a
class node_site_index,node_activations,node_backprop,node_gradient,node_momentum,node_adaptive_lr,node_regularisation,node_cnn,node_architectures,node_inception_resnet toneBlue
class node_cards,node_starter_notebook,node_instructor_materials toneAmber
class node_generator,node_experiment_configs,node_training_pipeline,node_calibration,node_experiment_summary toneMint
class node_kaggle_export,node_notebook_builder,node_card_renderer,node_card_code_builder toneRose
class node_learner toneIndigo
```

## Components

### Deep-learning worksheets

- [Worksheet index](https://github.com/kartikgupta98/dl-worksheets/blob/main/index.html): `index.html`
- [Activations](https://github.com/kartikgupta98/dl-worksheets/blob/main/activations.html): `activations.html`
- [Output-layer backprop](https://github.com/kartikgupta98/dl-worksheets/blob/main/backprop_worksheet_output_layer.html): `backprop_worksheet_output_layer.html`
- [Gradient descent](https://github.com/kartikgupta98/dl-worksheets/blob/main/lecture06_gradient_descent.html): `lecture06_gradient_descent.html`
- [Momentum and NAG](https://github.com/kartikgupta98/dl-worksheets/blob/main/worksheet07_momentum_nag.html): `worksheet07_momentum_nag.html`
- [Adaptive learning rates](https://github.com/kartikgupta98/dl-worksheets/blob/main/worksheet08_adaptive_lr.html): `worksheet08_adaptive_lr.html`
- [Regularisation lab](https://github.com/kartikgupta98/dl-worksheets/blob/main/worksheet09_regularisation.html): `worksheet09_regularisation.html`
- [CNN worksheet](https://github.com/kartikgupta98/dl-worksheets/blob/main/worksheet09_cnn.html): `worksheet09_cnn.html`
- [CNN architectures](https://github.com/kartikgupta98/dl-worksheets/blob/main/worksheet10_architectures.html): `worksheet10_architectures.html`
- [Inception and ResNet](https://github.com/kartikgupta98/dl-worksheets/blob/main/worksheet11_inception_resnet.html): `worksheet11_inception_resnet.html`

### Competition learning materials

- [Technique cards](https://github.com/kartikgupta98/dl-worksheets/blob/main/fraud_competition/materials/technique_cards.md): `fraud_competition/materials/technique_cards.md`
- [Student notebook](https://github.com/kartikgupta98/dl-worksheets/blob/main/fraud_competition/materials/starter_notebook.ipynb): `fraud_competition/materials/starter_notebook.ipynb`
- [Instructor materials](https://github.com/kartikgupta98/dl-worksheets/blob/main/fraud_competition/materials/instructor_guide.md): `fraud_competition/materials/instructor_guide.md`

### Data and calibration

- [Synthetic data generator](https://github.com/kartikgupta98/dl-worksheets/blob/main/fraud_competition/generate_data.py): `fraud_competition/generate_data.py`
- [Experiment configurations](https://github.com/kartikgupta98/dl-worksheets/blob/main/fraud_competition/exp2.py): `fraud_competition/exp2.py`
- [Modeling pipeline](https://github.com/kartikgupta98/dl-worksheets/blob/main/fraud_competition/pipeline.py): `fraud_competition/pipeline.py`
- [Calibration runner](https://github.com/kartikgupta98/dl-worksheets/blob/main/fraud_competition/calibrate.py): `fraud_competition/calibrate.py`
- [Experiment summary](https://github.com/kartikgupta98/dl-worksheets/blob/main/fraud_competition/summary.py): `fraud_competition/summary.py`

### Competition tooling

- [Kaggle export and scoring](https://github.com/kartikgupta98/dl-worksheets/blob/main/fraud_competition/export_kaggle.py): `fraud_competition/export_kaggle.py`
- [Notebook builder](https://github.com/kartikgupta98/dl-worksheets/blob/main/fraud_competition/make_notebooks.py): `fraud_competition/make_notebooks.py`
- [Card-page renderer](https://github.com/kartikgupta98/dl-worksheets/blob/main/fraud_competition/make_cards_html.py): `fraud_competition/make_cards_html.py`
- [Card-code notebook builder](https://github.com/kartikgupta98/dl-worksheets/blob/main/fraud_competition/make_card_code_notebook.py): `fraud_competition/make_card_code_notebook.py`

### Other components

- **Learner**

## Connections

- Learner → Worksheet index: opens (evidence: `README.md`)
- Worksheet index → Activations: links to (evidence: `README.md`)
- Worksheet index → Output-layer backprop: links to (evidence: `README.md`)
- Worksheet index → Gradient descent: links to (evidence: `README.md`)
- Worksheet index → Momentum and NAG: links to (evidence: `README.md`)
- Worksheet index → Adaptive learning rates: links to (evidence: `README.md`)
- Worksheet index → Regularisation lab: links to (evidence: `README.md`)
- Worksheet index → CNN worksheet: links to (evidence: `README.md`)
- Worksheet index → CNN architectures: links to (evidence: `README.md`)
- Worksheet index → Inception and ResNet: links to (evidence: `README.md`)
- Calibration runner → Synthetic data generator: generates data (evidence: `fraud_competition/calibrate.py`)
- Calibration runner → Experiment configurations: loads configs (evidence: `fraud_competition/calibrate.py`)
- Calibration runner → Modeling pipeline: runs models (evidence: `fraud_competition/calibrate.py`)
- Experiment configurations → Modeling pipeline: imports defaults (evidence: `fraud_competition/exp2.py`)
- Experiment summary → Calibration runner: uses summary (evidence: `fraud_competition/summary.py`)
- Kaggle export and scoring → Experiment configurations: uses settings (evidence: `fraud_competition/export_kaggle.py`)
- Kaggle export and scoring → Synthetic data generator: generates data (evidence: `fraud_competition/export_kaggle.py`)
- Kaggle export and scoring → Modeling pipeline: trains reference (evidence: `fraud_competition/export_kaggle.py`)
- Notebook builder → Modeling pipeline: uses pipeline (evidence: `fraud_competition/make_notebooks.py`)
- Notebook builder → Experiment configurations: uses configs (evidence: `fraud_competition/make_notebooks.py`)
- Card-page renderer → Technique cards: renders cards (evidence: `fraud_competition/make_cards_html.py`)
- Card-code notebook builder → Card-page renderer: uses card parser (evidence: `fraud_competition/make_card_code_notebook.py`)
- Card-code notebook builder → Notebook builder: uses notebook builder (evidence: `fraud_competition/make_card_code_notebook.py`)