Data Science

Independent Projects and Competition Submissions on Data Science, Machine and Deep Learning

Titanic Survival Prediction - Kaggle Link
- Position: Top 33% [78% Accuracy]
- Model: Random Forest (/w Parameter gridsearch)
- Data Preprocessing: Missing values and outliers removal (cleaning), replaced age data to categorical bins
MNIST Digit Recognizer - Kaggle Link
- Position: Top 18% [94.5% Accuracy] (91% without data augmentation)
- Model: CNN (Modified LeNet, 2Conv, 2FC)
- Data Preprocessing: Normalization and Data Augmentation (Translate and Rotate-Crop)
- Optimizer: SGD + momentum with Step LR decay
- Regularization: Dropout (0.2)
CIFAR-10 Image Classification - Kaggle Link
- Position: 81% Accuracy (74% without data augmentation)
- Model: CNN (4 Conv, 3FC)
- Optimizer: Adam with LR decay
- Data Preprocessing: Normalization and Data Augmentation (Translate, Rotate and Zoom)
- Regularization: Dropout (0.25) or BatchNormalisation [Both gave similar performance]
Facial Keypoint Detection - Kaggle Link
- Position: 2.456 (Mean Average Error)
- Model: CNN (3 Conv, 3FC)
- Optimizer: Adam with LR decay
- Data Preprocessing: Normalization
- Regularization: Dropout (0.25)

Name		Name	Last commit message	Last commit date
Latest commit History 32 Commits
.ipynb_checkpoints		.ipynb_checkpoints
CS231n/assignment1		CS231n/assignment1
data		data
results		results
Car_Sales_Predict.ipynb		Car_Sales_Predict.ipynb
DeepL.ipynb		DeepL.ipynb
MJ_Titanic_Age_Bins.ipynb		MJ_Titanic_Age_Bins.ipynb
MNIST_class_tf.ipynb		MNIST_class_tf.ipynb
PoseEstimation_TestBed.ipynb		PoseEstimation_TestBed.ipynb
README.md		README.md
car_sales.ipynb		car_sales.ipynb
cifar-10-cnn-adam.pth		cifar-10-cnn-adam.pth
cifar-10.ipynb		cifar-10.ipynb
cifar-10_tfkeras.ipynb		cifar-10_tfkeras.ipynb
datsci_lib.ipynb		datsci_lib.ipynb
ds_1.1.ipynb		ds_1.1.ipynb
lin_reg_first.ipynb		lin_reg_first.ipynb
mj_mnist_cnn_6.csv		mj_mnist_cnn_6.csv
mnist_inf_mj.pt		mnist_inf_mj.pt
mnist_mj_cnn_all.ipynb		mnist_mj_cnn_all.ipynb
mnist_mj_cnn_aug.ipynb		mnist_mj_cnn_aug.ipynb
mnist_mj_linear.ipynb		mnist_mj_linear.ipynb
mnist_mj_mod.pt		mnist_mj_mod.pt
model.pth		model.pth
model_cifar.h5		model_cifar.h5
model_cifar_da.h5		model_cifar_da.h5
opencv.py		opencv.py
optimizer.pth		optimizer.pth
preproc.ipynb		preproc.ipynb
quick_sort.ipynb		quick_sort.ipynb
scikit_LR.ipynb		scikit_LR.ipynb
tests.ipynb		tests.ipynb
tf_intro.ipynb		tf_intro.ipynb
tf_intro.npz		tf_intro.npz

Provide feedback