Download the free Kindle app and start reading Kindle books instantly on your smartphone, tablet, or computer - no Kindle device required.
Read instantly on your browser with Kindle for Web.
Using your mobile phone camera - scan the code below and download the Kindle app.
Follow the authors
Report an issue with this product or sellerFrequently bought together
Frequently purchased items with fast delivery
- Machine Learning From Scratch: Intuition, Math and Code of ML AlgorithmsPaperbackFREE Shipping on orders over $35 shipped by AmazonGet it as soon as Monday, Sep 21
- Python Machine Learning By Example: Unlock machine learning best practices with real-world use casesPaperbackFREE Shipping on orders over $35 shipped by AmazonGet it as soon as Monday, Sep 21
- Hands-On Machine Learning with Scikit-Learn and PyTorch: Concepts, Tools, and Techniques to Build Intelligent SystemsPaperbackFREE Shipping by AmazonGet it as soon as Saturday, Sep 19
- Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent SystemsPaperbackFREE Shipping by AmazonGet it as soon as Monday, Sep 21
- Deep Learning with PyTorch, Second Edition: Training and applying deep learning and generative AI modelsLuca AntigaPaperbackFREE Shipping by AmazonGet it as soon as Monday, Sep 21
- Mastering AI with Python: A Beginner’s Guide to Machine Learning, Deep Learning, Generative AI, LLMs, and AI AgentsPaperbackFREE Shipping on orders over $35 shipped by AmazonGet it as soon as Monday, Sep 21
From the brand
-
See more at our store:
-
Packt is a leading publisher of technical learning content with the ability to publish books on emerging tech faster than any other.
Our mission is to increase the shared value of deep tech knowledge by helping tech pros put software to work.
We help the most interesting minds and ground-breaking creators on the planet distill and share the working knowledge of their peers.
From the Publisher
What inspired you to write 'Mastering NLP from Foundations to LLMs?
Lior:
Our goal was to create a comprehensive guide that covers both the foundational and advanced aspects of NLP. We wanted to bridge the gap between theory and practice, providing readers with the mathematical foundations they need as well as practical, real-world applications.
Meysam:
We also wanted to highlight the latest trends in NLP and AI, particularly the rise of large language models (LLMs) and their transformative impact on the field. By the end of the book, readers will have a strong understanding of both the basics and cutting-edge advancements in NLP.
Your book delves into the mathematical foundations of NLP and machine learning. Why is understanding these foundations so crucial?
Meysam:
Understanding the mathematical foundations is essential because it provides the basis for all NLP techniques. Concepts like linear algebra, probability, and statistics are the building blocks that allow us to develop and optimize NLP algorithms effectively.
Lior:
Without a solid grasp of these fundamentals, it would be challenging to understand and implement more advanced techniques like those used in LLMs. These foundations help demystify complex models and make them more accessible.
Your book includes real-world use cases of NLP and LLMs. Can you share one of the most exciting applications you discussed?
Meysam:
One fascinating application is in healthcare. For instance, LLMs can be used to analyze patient data and assist in diagnosing diseases. They can also help in predicting patient outcomes by processing vast amounts of medical literature and clinical data.
Lior:
One example that comes to mind is from Chapter 9, where we put together a team of agents and ask them to generate conclusions from an analysis, we made simply by providing them the context and the aggregated results of the analysis. The agents demonstrated thoughtful judgement of the results by considering the tradeoffs and delivering a strong conclusion. We wanted to showcase the agents’ judgement to the reader, so we tasked the agents again with applying their judgement, but this time, we changed the aggregated results so to shift the balance of the tradeoffs, and indeed the agents picked up on that and provided an opposite conclusion to the prior case, just as would be expected.
These applications are truly transformative. How do you see the future of NLP and LLMs evolving in the next few years?
Lior:
We're seeing advancements being made around leveraging multiple LLMs. There are several different paradigms to that, and we touch on those in Chapter 9. One example is the use of multiple LLMs in parallel in the form of multi agent teams, collaborating with each other. We see this approach yielding better results. In different cases we see a switching systems picking which LLM to deploy for every particular call. In this setting, each LLM is different, so there’s a tradeoff between the LLM that is perhaps cheaper, but more specific in its capability, than a more expensive and maybe slower LLM that may have a broader “knowledge base.” The decision is then made based on the incoming prompt, current system balance, cost, required speed, etc. This then works to optimize the various factors of the operation.
Meysam:
Additionally, as these models become more efficient and accessible, we expect to see wider adoption, driving innovation and solving complex problems in new ways.
