Neural networks have progressed enough to comprehend large amounts of text and generate entire sequences in continuation to a short input prompt. This notion has found immense use in generating product descriptions, promotional emails and also to generate training data to create models that can detect whether a given text was generated by AI. While models like GPT-3 have achieved the benchmark in this task, we can start from scratch using LSTMs. You can use text from the free ebooks available on Project Gutenberg. After cleaning and vectorizing the data, we can train a Sequential LSTM model on several batches of sentences. Once that is done, you can give the model a test sequence from the ebook and map the output vectors with the character set. You will see that the model was able to continue your input prompt and generate (hopefully) meaningful and relevant sentences.

James Loy has more than five years, expert experience in data science in the finance and healthcare industries. He has worked with the largest bank in Singapore to drive innovation and improve customer loyalty through predictive analytics. He has also experience in the healthcare sector, where he applied data analytics to improve decision-making in hospitals. He has a master's degree in computer science from Georgia Tech, with a specialization in machine learning. His research interest includes deep learning and applied machine learning, as well as developing computer-vision-based AI agents for automation in industry.