Embark on an exciting journey into deep learning for text with PyTorch. This course will equip you with the skills to tackle various text-related challenges. You'll dive into the principles of text processing with encoding and embedding. You’ll apply various models, including CNNs, RNNs, GANs, and pre-trained models, using text data. Finally, you'll delve into advanced topics, including transfer learning techniques, attention mechanisms, and how to protect your models from adversarial attacks. By the end of this course, you'll have the skills to build powerful deep learning models for text.
Introduction to Deep Learning for Text with PyTorchFree
This chapter introduces you to deep learning for text and its applications. Learn how to use PyTorch for text processing and get hands-on experience with techniques such as tokenization, stemming, stopword removal, and more. Understand the importance of encoding text data and implement encoding techniques using PyTorch. Finally, consolidate your knowledge by building a text processing pipeline combining these techniques.Introduction to preprocessing for text50 xpWord frequency analysis100 xpPreprocessing text100 xpEncoding text data50 xpOne-hot encoded book titles100 xpBag-of-words for book titles100 xpApplying TF-IDF to book descriptions100 xpIntroduction to building a text processing pipeline50 xpShakespearean language preprocessing pipeline100 xpShakespearean language encoder100 xp
Text Classification with PyTorchFree
Explore text classification and its role in Natural Language Processing (NLP). Apply your skills to implement word embeddings and develop both Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) for text classification using PyTorch, and understand how to evaluate your models using suitable metrics.Overview of Text Classification50 xpEmbedding in PyTorch100 xpCategorizing text classification tasks100 xpConvolutional neural networks for text classification50 xpBuild a CNN model for text100 xpTrain a CNN model for text100 xpTesting the Sentiment Analysis CNN Model100 xpRecurrent neural networks for text classification50 xpBuilding an RNN model for text100 xpBuilding an LSTM model for text100 xpBuilding a GRU model for text100 xpEvaluation metrics for text classification50 xpEvaluating RNN classification models100 xpEvaluating the model's performance100 xpComparing models50 xp
Text Generation with PyTorch
Venture into the exciting world of text generation and its applications in NLP. Understand how to leverage Recurrent Neural Networks (RNNs), Generative Adversarial Networks (GANs), and pre-trained models for text generation tasks using PyTorch. Alongside, you'll learn to evaluate the performance of your models using relevant metrics.Introduction to text generation50 xpCreating a RNN model for text generation100 xpText generation using RNN - Training and Generation100 xpGenerative adversarial networks for text generation50 xpBuilding a generator and discriminator100 xpTraining a GAN model100 xpPre-trained models for text generation50 xpText completion with pre-trained GPT-2 models100 xpLanguage translation with pretrained PyTorch model100 xpEvaluation metrics for text generation50 xpEvaluating pretrained text generation model100 xpUnderstanding text generation metrics50 xp
Advanced Topics in Deep Learning for Text with PyTorch
Understand the concept of transfer learning and its application in text classification. Explore Transformers, their architecture, and how to use them for text classification and generation tasks. You will also delve into attention mechanisms and their role in text processing. Finally, understand the potential impacts of adversarial attacks on text classification models and learn how to protect your models.Transfer learning for text classification50 xpTransfer learning using BERT100 xpEvaluating the BERT model100 xpTransformers for text processing50 xpCreating a transformer model100 xpTraining and testing the Transformer model100 xpAttention mechanisms for text processing50 xpCreating a RNN model with attention100 xpTraining and testing the RNN model with attention100 xpAdversarial attacks on text classification models50 xpAdversarial attack classification100 xpSafeguarding AI at PyBooks50 xpWrap-up50 xp
Audio Recorded By
PrerequisitesIntermediate Deep Learning with PyTorch
Shubham JainSee More
A dynamic and dedicated Artificial Intelligence Researcher and Lecturer, Shubham's expertise lies in Data Science, Machine Learning, Artificial Intelligence, and Software Development applications, skills honed through a rich history of roles in prestigious institutions and companies. Currently, he is pursuing a Ph.D. in Computer Science from the Technological University of Shannon, where he also imparts knowledge as a part-time lecturer, alongside a similar role at the UCD Professional Academy. In the corporate sphere, Shubham has made significant strides, holding the position of Senior Data Scientist at Mastercard and previously contributing as a Senior Researcher at Ericsson. A thought leader in his field, Shubham has presented groundbreaking research in renowned conferences and holds patents in innovative areas of Artificial Intelligence and Machine Learning.