Vladimir Cuc
I have gained significant experience in AI through my machine learning classes and various personal projects. In these projects, I have extensively used Python and several key libraries, including scikit-learn, Keras, PyTorch, and Matplotlib. My work has allowed me to explore a wide range of machine learning algorithms, further enhancing my skills and understanding of AI applications.
In this course, I learned key machine learning models and methods, including regression, neural networks, and support vector machines. I also gained hands-on experience using Python and advanced libraries like PyTorch and Keras to build and train neural networks, strengthening my practical skills in AI applications.
In this class, I explored advanced AI topics like evolutionary computation, neural networks, and gaming strategies. I gained practical experience with PCA for face recognition, K-means clustering, and developed skills using scikit-learn and Matplotlib for data visualization and machine learning tasks.
Utilized Principal Component Analysis (PCA), K-Means clustering, and Nearest Neighbors to analyze a dataset of 839 Survivor contestants' faces, predicting professor attributes by comparing facial features. Reduced dimensionality while retaining 90% variance, and employed clustering techniques to explore the link between facial features and traits.
GithubIn this project, neural network models were created using PyTorch and Keras to predict diabetes from a Kaggle dataset. Trained on 2,460 instances and tested on 308, the models utilized key health indicators such as glucose, BMI, and insulin to generate binary predictions of diabetes presence.
GithubThis project trained and tested K-Nearest Neighbors (KNN) and Support Vector Machine (SVM) algorithms on the MNIST dataset of 70,000 handwritten digit images. The models aimed to accurately classify digits from 0 to 9 using 60,000 training images and 10,000 for testing.
Github
