Skip to content

Repository of Notes & Projects to the Udacity Deep Learning Nanodegree Course. Also includes Mathematics Q&As for Data Science.

Notifications You must be signed in to change notification settings

jordan-carson/DeepLearning

Repository files navigation

Deep Learning & Mathematics for Data Science

by Jordan Carson

This repository holds practice problems and solutions to Deep Learning & Machine Learning problems. Additionally, I have also saved most mathematics notes for Data Science, within this repository.

This repository structure was built off Udacity Deep Learning Nanodegree.

Deep Learning Machine Learning Notes for Data Science Topics

More to Come!

TODO: Mathematics, Include Machine Learning Notes from Udacity Machine Learning Nanodegree / Artificial Intelligence Nanodegreee

Directory Tree

├── Notes
│   ├── 0.\ Applications\ &\ Tools
│   │   ├── Docker\ Cheat\ Sheet.pdf
│   │   ├── Interview\ Questions.pdf
│   │   ├── Linux.png
│   │   ├── SQL-cheat-sheet.pdf
│   │   ├── atlassian-git-cheatsheet.pdf
│   │   └── docker\ CLI\ &\ Dockerfile\ Cheat\ Sheet.pdf
│   ├── 0.\ Artificial\ Intelligence
│   │   └── super-cheatsheet-artificial-intelligence.pdf
│   ├── 0.\ Data\ Analysis
│   │   └── pandas_cheat_sheet.pdf
│   ├── 0.\ Data\ Engineering
│   ├── 0.\ Deep\ Learning
│   ├── 0.\ Machine\ Learning
│   │   ├── Cheat\ Sheet\ Algorithms\ for\ Supervised\ and\ Unsupervised\ Learning.pdf
│   │   ├── Esssential\ ML\ Algo\ cheat\ sheet.pdf
│   │   ├── Handling\ imbalanced\ datasets.pdf
│   │   ├── ML\ PROS\ N\ CONS.pdf
│   │   ├── ML\ VIP\ Cheat\ Sheat.pdf
│   │   ├── Machine\ Learning\ Cheatsheet.pdf
│   │   ├── Machine\ Learning\ Cheatsheet_NEW.pdf
│   │   └── rules_of_ml.pdf
│   └── 0.\ Mathematics
│       ├── Algebra_Cheat_Sheet.pdf
│       ├── Linear\ Algebra\ and\ Calculus.pdf
│       ├── Statistics\ Cheat\ Sheet.pdf
│       ├── calculus.pdf
│       ├── cheatsheet-statistics.pdf
│       ├── linear-algebra.pdf
│       └── trigonometry.pdf
├── README.md
├── deep_learning
│   ├── 1.\ Intro\ to\ Deep\ Learning
│   │   ├── Notes.ipynb
│   │   └── keyboard-shortcuts.ipynb
│   ├── 2.\ Neural\ Networks
│   │   ├── L2.\ Gradient\ Descent
│   │   │   └── Notes.ipynb
│   │   ├── L3.\ Training\ Neural\ Networks
│   │   │   ├── Notes.ipynb
│   │   │   ├── data
│   │   │   │   ├── binary.csv
│   │   │   │   ├── error_question.png
│   │   │   │   ├── error_question2.png
│   │   │   │   ├── gradient.png
│   │   │   │   ├── hj.png
│   │   │   │   ├── local_minima.png
│   │   │   │   ├── multi_layer_perceptron.png
│   │   │   │   ├── network.png
│   │   │   │   ├── regularization.png
│   │   │   │   ├── sigmoid.png
│   │   │   │   ├── weights_firsthidden.png
│   │   │   │   ├── weights_network.png
│   │   │   │   └── weights_network1.png
│   │   │   └── sentiment-analysis-network
│   │   │       ├── Sentiment_Classification_Projects.ipynb
│   │   │       ├── Sentiment_Classification_Solutions.ipynb
│   │   │       ├── labels.txt
│   │   │       ├── sentiment_network.png
│   │   │       ├── sentiment_network_2.png
│   │   │       ├── sentiment_network_pos.png
│   │   │       ├── sentiment_network_sparse.png
│   │   │       └── sentiment_network_sparse_2.png
│   │   ├── L6.\ Sentiment\ Analysis
│   │   ├── L7.\ Deep\ Learning\ with\ PyTorch
│   │   │   ├── Notes.ipynb
│   │   │   └── intro-to-pytorch
│   │   │       ├── Part\ 1\ -\ Tensors\ in\ PyTorch\ (Exercises).ipynb
│   │   │       ├── Part\ 1\ -\ Tensors\ in\ PyTorch\ (Solution).ipynb
│   │   │       ├── Part\ 2\ -\ Neural\ Networks\ in\ PyTorch\ (Exercises).ipynb
│   │   │       ├── Part\ 2\ -\ Neural\ Networks\ in\ PyTorch\ (Solution).ipynb
│   │   │       ├── Part\ 3\ -\ Training\ Neural\ Networks\ (Exercises).ipynb
│   │   │       ├── Part\ 3\ -\ Training\ Neural\ Networks\ (Solution).ipynb
│   │   │       ├── Part\ 4\ -\ Fashion-MNIST\ (Exercises).ipynb
│   │   │       ├── Part\ 4\ -\ Fashion-MNIST\ (Solution).ipynb
│   │   │       ├── Part\ 5\ -\ Inference\ and\ Validation\ (Exercises).ipynb
│   │   │       ├── Part\ 5\ -\ Inference\ and\ Validation\ (Solution).ipynb
│   │   │       ├── Part\ 6\ -\ Saving\ and\ Loading\ Models.ipynb
│   │   │       ├── Part\ 7\ -\ Loading\ Image\ Data\ (Exercises).ipynb
│   │   │       ├── Part\ 7\ -\ Loading\ Image\ Data\ (Solution).ipynb
│   │   │       ├── Part\ 8\ -\ Transfer\ Learning\ (Exercises).ipynb
│   │   │       ├── Part\ 8\ -\ Transfer\ Learning\ (Solution).ipynb
│   │   │       ├── README.md
│   │   │       ├── checkpoint.pth
│   │   │       ├── fc_model.py
│   │   │       └── helper.py
│   │   ├── Neural\ Networks.ipynb
│   │   ├── Notes.md
│   │   ├── Project_BikeSharing
│   │   │   ├── Your_first_neural_network.ipynb
│   │   │   ├── __pycache__
│   │   │   ├── data
│   │   │   │   ├── day.csv
│   │   │   │   └── hour.csv
│   │   │   └── my_answers.py
│   │   └── Untitled.ipynb
│   ├── 3.\ Convolutional\ Neural\ Networks
│   │   ├── L1.\ Convolutional\ Neural\ Networks
│   │   │   ├── Notes.ipynb
│   │   │   ├── Untitled.ipynb
│   │   │   ├── cifar_example.py
│   │   │   └── data
│   │   │       └── cifar-10-batches-py
│   │   │           ├── batches.meta
│   │   │           ├── data_batch_1
│   │   │           ├── data_batch_2
│   │   │           ├── data_batch_3
│   │   │           ├── data_batch_4
│   │   │           ├── data_batch_5
│   │   │           ├── readme.html
│   │   │           └── test_batch
│   │   ├── L2.\ Cloud\ Computing
│   │   ├── L3.\ Transfer\ Learning
│   │   │   └── Untitled.ipynb
│   │   ├── L4.\ Weight\ Initialization
│   │   ├── L5.\ Autoencoders
│   │   ├── L6.\ Style\ Transfer
│   │   ├── Notes.ipynb
│   │   ├── convolutional-neural-networks
│   │   │   ├── cifar-cnn
│   │   │   │   ├── cifar10_cnn_augmentation.ipynb
│   │   │   │   ├── cifar10_cnn_exercise.ipynb
│   │   │   │   ├── cifar10_cnn_solution.ipynb
│   │   │   │   └── notebook_ims
│   │   │   │       ├── 2_layer_conv.png
│   │   │   │       └── cifar_data.png
│   │   │   ├── conv-visualization
│   │   │   │   ├── conv_visualization.ipynb
│   │   │   │   ├── custom_filters.ipynb
│   │   │   │   ├── data
│   │   │   │   │   ├── bridge_trees_example.jpg
│   │   │   │   │   ├── curved_lane.jpg
│   │   │   │   │   ├── sobel_ops.png
│   │   │   │   │   ├── udacity_sdc.png
│   │   │   │   │   └── white_lines.jpg
│   │   │   │   ├── maxpooling_visualization.ipynb
│   │   │   │   └── notebook_ims
│   │   │   │       ├── CNN_all_layers.png
│   │   │   │       ├── maxpooling_ex.png
│   │   │   │       ├── relu_ex.png
│   │   │   │       └── sobel_ops.png
│   │   │   └── mnist-mlp
│   │   │       ├── mnist_mlp_exercise.ipynb
│   │   │       ├── mnist_mlp_solution.ipynb
│   │   │       └── mnist_mlp_solution_with_validation.ipynb
│   │   ├── data
│   │   │   ├── cnn_loss.png
│   │   │   ├── convolutional_layer.png
│   │   │   └── relu.png
│   │   ├── first_example.py
│   │   └── project-dog-classification
│   │       ├── README.md
│   │       ├── dog_app.ipynb
│   │       ├── haarcascades
│   │       │   └── haarcascade_frontalface_alt.xml
│   │       └── images
│   │           ├── American_water_spaniel_00648.jpg
│   │           ├── Brittany_02625.jpg
│   │           ├── Curly-coated_retriever_03896.jpg
│   │           ├── Labrador_retriever_06449.jpg
│   │           ├── Labrador_retriever_06455.jpg
│   │           ├── Labrador_retriever_06457.jpg
│   │           ├── Welsh_springer_spaniel_08203.jpg
│   │           ├── sample_cnn.png
│   │           ├── sample_dog_output.png
│   │           └── sample_human_output.png
│   ├── 4.\ Recurrent\ Neural\ Networks
│   │   ├── L1.\ Recurrent\ Neural\ Networks
│   │   │   ├── Notes.ipynb
│   │   │   ├── backprop.png
│   │   │   ├── backprop_ex.png
│   │   │   ├── chain_rule_quiz.png
│   │   │   ├── cnns_with_rnns.png
│   │   │   ├── feedforward_cycle.png
│   │   │   ├── generating_the_output.png
│   │   │   ├── gradient_calc2.png
│   │   │   ├── gradient_calculation.png
│   │   │   ├── gradient_pt1.png
│   │   │   ├── gradient_pt3.png
│   │   │   ├── network_function_map.png
│   │   │   ├── neural_network_task.png
│   │   │   └── w1_math.png
│   │   ├── L2.\ Long\ Short-Term\ Memory\ Networks\ (LSTMs)
│   │   ├── L3.\ Implementation\ of\ RNN\ &\ LSTM
│   │   └── L4.\ Hyperparameters
│   ├── 5.\ Generative\ Adversarial\ Networks
│   │   ├── L1.\ Generative\ Adversarial\ Networks
│   │   ├── L2.\ Deep\ Convolutional\ GANs
│   │   ├── L3.\ Pix2Pix\ &\ CycleGan
│   │   ├── L4.\ Implementing\ a\ CycleGAN
│   │   └── Project-Generate\ Faces
│   ├── 6.\ Deploying\ a\ Model
│   │   ├── L1.\ Introduction\ to\ Deployment
│   │   ├── L2.\ Building\ a\ Model\ using\ SageMaker
│   │   ├── L3.\ Deploying\ and\ Using\ a\ Model
│   │   ├── L4.\ Hyperparameter\ Tuning
│   │   ├── L5.\ Updating\ a\ Model
│   │   └── Project-Deploying\ a\ Sentiment\ Analysis\ Model
│   ├── Mathematics\ for\ Deep\ Learning.ipynb
│   ├── Untitled.ipynb
│   ├── functions.py
│   └── workspace_utils.py
├── machine_learning
│   ├── 1.\ Machine\ Learning\ Foundations
│   ├── 2.\ Supervised\ Learning
│   ├── 3.\ Unsupervised\ Learning
│   ├── 4.\ Reinforcement\ Learning
│   ├── 5.\ Deep\ Learning
│   └── Top\ Machine\ Learning\ Questions.ipynb
├── mathematics
│   ├── 1.\ Statistics
│   ├── 2.\ Probability
│   ├── 3.\ Linear\ Algebra
│   ├── 4.\ Single\ Variable\ Calculus
│   └── 5.\ Multi-Variable\ Calculus
└── utilities
    ├── __init__.py
    ├── __pycache__
    │   └── __init__.cpython-36.pyc
    ├── data_blend
    │   ├── __pycache__
    │   │   ├── db_utilities.cpython-36.pyc
    │   │   └── operations.cpython-36.pyc
    │   ├── db_utilities.py
    │   └── operations.py
    ├── fn.py
    └── training
        └── helpers.py

About

Repository of Notes & Projects to the Udacity Deep Learning Nanodegree Course. Also includes Mathematics Q&As for Data Science.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published