By the end of this course, learners will prepare image and text datasets, construct classification models, train neural networks, evaluate model performance, and apply transformer architectures for text generation. This practical course explores two major applications of deep learning: computer vision and natural language processing. Learners will download, transform, normalize, and visualize image datasets before defining, training, and testing classifiers using MNIST and CIFAR-10. They will also configure neural network layers, loss functions, inputs, outputs, and training loops. The second part introduces text classification using convolutional neural networks.
Learners will prepare textual data, build and optimize classification models, experiment with loss functions, and evaluate model results. They will then explore text generation and the fundamental architecture of transformers. Completing this course will enable learners to build end-to-end deep learning workflows for image and text applications. Its unique strength is the combination of computer vision and NLP within one project-focused learning experience, allowing learners to compare how neural networks process visual and language-based data.
