This repository contains the projects I completed for the Udacity Machine Learning Engineer Nanodegree. The original repository for the curriculum is here.
- Summary: Classify dermoscopic images among nine different diagnostic categories without meta-data.
- Keywords: Convolutional Neural Network (CNN), Transfer Learning, Fine-Tuning, Ensemble Model, Out-of-Distribution Detection
- Summary: Predict the value of houses using decision tree regression, grid search, and k-fold cross validation.
- Keywords: Decision Tree Regression, Grid Search, K-fold Cross Validation, R2 Score (Coefficient of Determination), Supervised Learning, Pandas, Scikit-learn
- Summary: Evaluate and optimize several supervised learning models to predict whether an individual makes more than $50,000 based on the 1994 U.S. census data.
- Keywords: Skewed Distributions, Data Transformation, Preprocessing, F-beta Score, Logistic Regression, Support Vector Machines (SVMs), Gradient Boosting, Feature Selection
- Summary: Apply unsupervised learning algorithms on product spending data collected for customers of a wholesale distributor to identify customer segments hidden in the data.
- Keywords: Unsupervised Learning, K-means, Feature Relevance, Correlation Matrix, Log-normal Distribution, Feature Scaling, Outlier Detection, Tukey Method, Feature Transformation, Principal Component Analysis (PCA), Dimensionality Reduction, Biplot, Gaussian Mixture Model (GMM), Silhouette Coefficient, Elbow Method, Adjusted Rand Index
- Summary: Given an image of a dog, the algorithm will identify an estimate of the canine’s breed. If supplied an image of a human, the code will identify the resembling dog breed.
- Keywords: Convolutional Neural Network (CNN), OpenCV, Face Detection, Haar Cascades, Single Shot MultiBox Detector (SSD), ResNet-50, Xception, Keras, TensorFlow, Bottleneck Features, Transfer Learning, Dropout
- Udacity Repo: https://github.com/udacity/dog-project
- Summary: Build a quadcopter flying agent that learns to take off vertically from any initial position using reinforcement learning.
- Keywords: Reinforcement Learning (RL), State, Action, Reward Function, Deep Deterministic Policy Gradient (DDPG), Actor-Critic, Experience Replay, Ornstein–Uhlenbeck Noise
- Udacity Repo: https://github.com/udacity/RL-Quadcopter-2