Intellect PlusAI & machine learning: practical
23 cards. Each one is a 40-second story with a five-minute read behind it.
Is your smartphone actually thinking or just very good at math?We often speak of AI as a singular entity, but it is actually a layered hierarchy of technologies. While we are still far from achieving conscious machines, the systems powering o…
Machine learning is not a replacement for AI, but its enginePeople often use the terms AI and machine learning interchangeably, but they represent different scales of technology. While AI is the broad ambition of mimicking human cognition,…
Why mastering machine learning is a marathon, not a sprintAspiring engineers often fall for the trap of quick-fix tutorials. This video provides a realistic roadmap for mastering machine learning by focusing on long-term depth over short…
From $21B to $209B: The invisible growth of machine learningMachine learning is no longer a futuristic concept; it is a massive global industry woven into the fabric of daily life. This video explores how these technologies move from data …- Navigating the path to mastery in machine learning todayMarina Wyss shares a personal roadmap for mastering machine learning in 2026. If you are looking to transition into AI engineering or start from scratch, this guide distills her p…
Computers that learn without being explicitly programmedThis video introduces the core mechanics of machine learning, a sub-field of artificial intelligence. It explains how systems transition from static code to self-learning programs…- From Linear Regression to Neural Networks in 17 minutesThis video provides a comprehensive overview of the machine learning landscape. It is designed to build an intuitive understanding of how different algorithms function and how the…
Demystifying the layers of modern artificial intelligenceMost people use AI as a catch-all term, but it actually describes a nested hierarchy of technologies. This video clarifies the specific distinctions between AI, machine learning, …
How do computers read text using a tokenizer?Transformer models cannot understand raw text directly. You will learn how a tokenizer acts as a bridge, converting human language into numerical data that a neural network can pr…
How AI Agents Use Tools and PromptsUnderstand the core architecture of an AI agent by exploring how they combine large language models with external tools and structured instructions to perform complex tasks.
How a model reaches convergenceYou can track a machine learning model's progress by watching its loss curve. Understanding this process helps you know exactly when your training has finished successfully.
Automating Model Sharing with the push_to_hub APILearn how to seamlessly sync your machine learning models to a central repository. Understanding this mechanism allows you to automate version control and metadata generation duri…- How a Large Language Model predicts the next piece of textYou use them every day to write emails or code, but how do these massive AI models actually function? Learn the fundamental mechanism behind the text generation that powers modern…
- How to read machine learning learning curvesBy analyzing the shape of loss and accuracy curves, you can determine if your model is learning effectively, overfitting to your data, or failing to capture essential patterns.
How attention mechanisms handle long sequencesStandard AI models struggle with long texts because their computational needs grow quadratically. You will learn how specialized attention mechanisms use sparsity to process much …
Choosing the right framework for LLM deploymentDeciding how to serve large language models depends on your hardware and goals. You will learn how to distinguish between TGI, vLLM, and llama.cpp to optimize for production stabi…
How a manual machine learning training loop functionsInstead of relying on high-level automated tools, you can build a training loop from scratch. Understanding this process helps you master how data, models, and optimizers interact…- How to control how AI chooses its next wordsLarge language models don't just pick words; they navigate a landscape of probabilities. By adjusting sampling strategies, you can transform an AI from a rigid, precise tool into …
- How to deploy a local LLM serverLearn how to set up a local inference server using frameworks like TGI. You will understand how to host a model on your own machine and interact with it using standard Python clie…
How to fine-tune models using the Trainer APIYou can adapt pretrained models to specific tasks like sequence classification by using the Transformers Trainer class. This approach automates modern best practices, saving you f…
How to upload model files to the Hugging Face HubLearn how to share your pretrained models with the community. You will understand how to use the huggingface_hub library to push files directly to a repository without needing com…
How Transformer models process and predict languageYou will understand the underlying mechanics of Transformer architectures. Learning how these models use context to predict words helps demystify the technology driving modern AI …
How Transformers Process Audio into TextUnderstand how models like Whisper transform raw sound into written words by treating audio as a sequence, similar to how they process text.