A practical introduction to neural network algorithms and their applications in machine learning using Python. Supervised learning (logistic regression, perceptrons, classification, trees, cost functions, non-linear regression, boosting) and unsupervised learning (autoencoder, principal component analysis, clustering, k-means) will be discussed. Students will conduct a series of projects to explore topics such as optimization, spam classification, image recognition, fraud detection and medical data analysis.
A practical introduction to neural network algorithms and their applications in machine learning using Python. Supervised learning (logistic regression, perceptrons, classification, trees, cost functions, non-linear regression, boosting) and unsupervised learning (autoencoder, principal component analysis, clustering, k-means) will be discussed. Students will conduct a series of projects to explore topics such as optimization, spam classification, image recognition, fraud detection and medical data analysis.
