Courses completed between November 2019 and Jan 2020.
Machine Learning with Python: This course covered the purpose of Machine Learning and where it applied to the real world and a general overview of Machine Learning topics such as supervised vs unsupervised learning, model evaluation, and Machine Learning algorithms(Regression, Classification, Clustering, Recommender Systems). For the final project, a set of past loan data was provided and expected to analyze and preprocess the dataset before building a classifier to predict whether a loan case will be paid off or not.
Scalable Machine Learning on Big Data using Apache Spark: Most real-world machine learning work involved very large datasets that go beyond a single computer’s CPU, memory, and storage. Apache Spark is an open-source framework that leverages cluster computing and distributed storage to process extremely large datasets. This course taught me the skills to scale data science and machine learning to take big datasets using Apache Spark. By the end of the course, we learned how to use Apache Spark for dataset processing and apply statistical calculations using the Apache Spark RDD API. Also learned the concept of machine learning pipelines and how to apply supervised and unsupervised machine learning tasks using SparkML.
Introduction to Deep Learning & Neural Networks with Keras: The course topics were the introduction to Neural Networks and Deep Learning, Artificial Neural Networks, Keras and Deep Learning Libraries, Deep Learning Models, and Course Project. As the final course project, we built a regression model using the deep learning Keras library and measured the impacts of the performance of the model after we tuning the number of hidden layers or the number of training epochs.
Deep Neural Networks with PyTorch: We learned how to build deep learning models using Pytorch. The topics were Tensor and Datasets, Linear Regression, Linear Regression PyTorch Way, Multiple Input Output Linear Regression, Logistic Regression for Classification, Softmax Regression, Shallow Neural Networks, Deep Networks, Convolutional Neural Network, and Course Project. For the course project, we trained a convolutional neural network to recognize images from fashion MNIST and created the dataset object to get higher accuracy on validation data.
Building Deep Learning Models with TensorFlow: The course taught foundational TensorFlow concepts and how to build models for supervised and unsupervised learning using TensorFlow. For supervised deep learning models, we learned about Convolutional Neural Network, Recurrent Neural Network, and Recursive Neural Tensor Network theory and applied recurrent neural networks to language modeling. For unsupervised deep learning models, we learned about Restricted Boltzmann Machines(RBMs) and built a recommendation system using RBMs. Also learned about autoencoders and architecture.
AI Capstone Project with Deep Learning: We demonstrated our deep learning knowledge and learning to solve a real-world challenge. We loaded and processed the image data, selected a pre-trained model(PyTorch: ResNet 18 pre-train model and Keras: VGG16 pre-trained model), and validated the model. We presented our project report to demonstrate the validity of our model and our proficiency in the field of deep learning.