<\/strong>It\u2019s fairly rare for an author\u2019s TDS debut to become one of the most popular articles of the month, but Giuseppe Scalamogna<\/a>\u2019s article pulled off this feat thanks to an accessible and timely explainer on program simulation: a prompt-engineering technique that \u201caims to make ChatGPT operate in a way that simulates a program,\u201d and can lead to impressive results.<\/li>\n\n\n\n
<\/strong>Tutorials on neural networks are easy to find. Less common? A step-by-step guide that helps readers gain both an intuitive understanding of how they work, and<\/em> the practical know-how for coding them from scratch. Callum Bruce<\/a> delivered precisely that in his latest contribution.<\/li>\n\n\n\n
<\/strong>If you\u2019ve already discovered Khouloud El Alami<\/a>\u2019s writing, you won\u2019t be surprised to learn her most recent post offers actionable insights presented in an accessible and engaging way. This one is geared towards data scientists at the earliest stages of their career: if you\u2019re not sure how to set yourself on the right path, Khouloud\u2019s advice will help you find your bearings.<\/li>\n<\/ul>\n\n\n\n
- \n
- How to Design a Roadmap for a Machine Learning Project<\/strong><\/a>
<\/strong>For those of you who are already well into your ML journey, Heather Couture<\/a>\u2019s new article offers a helpful framework for streamlining the design of your next project. From a robust literature review to post-deployment maintenance, it covers all the bases for a successful, iterative workflow.<\/li>\n\n\n\n- Machine Learning\u2019s Public Perception Problem<\/strong><\/a>
<\/strong>In a thought-provoking reflection, Stephanie Kirmer<\/a> tackles a fundamental tension in the current debates around AI: \u201call our work in the service of building more and more advanced machine learning is limited in its possibility not by the number of GPUs we can get our hands on but by our capacity to explain what we build and educate the public on what it means and how to use it.\u201d<\/li>\n\n\n\n- How to Build an LLM from Scratch<\/strong><\/a>
<\/strong>Taking a cue from the development process of models like GPT-3 and Falcon, Shawhin Talebi<\/a> reviews the key aspects of creating a foundation LLM. Even if you\u2019re not planning to train the next Llama anytime soon, it\u2019s valuable to understand the practical considerations that go into such a massive undertaking.<\/li>\n\n\n\n- Your Own Personal ChatGPT<\/strong><\/a>
<\/strong>If you are<\/em> in the mood for building and tinkering with language models, however, a great place to start is Robert A. Gonsalves<\/a>\u2019s detailed overview of what it takes to fine-tune OpenAI\u2019s GPT-3.5 Turbo model to perform new tasks using your own custom data.<\/li>\n\n\n\n- How to Build a Multi-GPU System for Deep Learning in 2023<\/strong><\/a>
<\/strong>Don\u2019t roll down your sleeves just yet\u2014one of our most-read tutorials in September, by Antonis Makropoulos<\/a>, focuses on deep-learning hardware and infrastructure, and walks us through the nitty-gritty details of choosing the right components for your project\u2019s needs.<\/li>\n\n\n\n- Meta-Heuristics Explained: Ant Colony Optimization<\/strong><\/a>
<\/strong>For a more theoretical\u2014but no less fascinating\u2014topic, Hennie de Harder<\/a>\u2019s introduction to ant-colony optimization draws our attention to a \u201clesser-known gem\u201d of an algorithm, explores how it took inspiration from the ingenious foraging behaviors of ants, and unpacks its inner workings. (In a follow-up post<\/a>, Hennie also demonstrates how it can solve real-world problems.)<\/li>\n\n\n\n- Falcon 180B: Can It Run on Your Computer?<\/strong><\/a>
<\/strong>Closing on an ambitious note, Benjamin Marie<\/a> sets out to find out if one can run the (very, very large) Falcon 180B model on consumer-grade hardware. (Spoiler alert: yes, with a couple of caveats.) It\u2019s a valuable resource for anyone who\u2019s weighing the pros and cons of working on a local machine vs. using cloud services\u2014especially now that more and more open-source LLMs are arriving on the scene.<\/li>\n<\/ul>\n\n\n\n
\n\n\n\n - Machine Learning\u2019s Public Perception Problem<\/strong><\/a>