From 272661fd343b2f6299dde357029dad841d2a69f9 Mon Sep 17 00:00:00 2001 From: Michele Cereda Date: Thu, 19 Feb 2026 22:09:28 +0100 Subject: [PATCH] chore(kb/ai): review and expand notes --- knowledge base/ai/README.md | 6 +- knowledge base/ai/claude/claude code.md | 4 +- knowledge base/ai/ml.md | 102 ++++++++++++++++++++++++ 3 files changed, 109 insertions(+), 3 deletions(-) create mode 100644 knowledge base/ai/ml.md diff --git a/knowledge base/ai/README.md b/knowledge base/ai/README.md index 8af4ce9..a2d46c4 100644 --- a/knowledge base/ai/README.md +++ b/knowledge base/ai/README.md @@ -14,10 +14,11 @@ speech recognition, decision-making and language translation. ## Further readings +- [Machine learning] - [Large Language Model] (LLM) - [Model Context Protocol] (MCP) - [Useful AI]: tools, courses, and more, curated and reviewed by experts. -- geeksforgeeks.com's [Artificial Intelligence Tutorial][geeksforgeeks artificial intelligence tutorial] +- geeksforgeeks.com's [Artificial Intelligence Tutorial][geeksforgeeks/artificial intelligence tutorial] ### Sources @@ -29,10 +30,11 @@ speech recognition, decision-making and language translation. [Large Language Model]: llm.md +[Machine learning]: ml.md [Model Context Protocol]: mcp.md -[geeksforgeeks Artificial Intelligence Tutorial]: https://www.geeksforgeeks.org/artificial-intelligence/ +[geeksforgeeks/Artificial Intelligence Tutorial]: https://www.geeksforgeeks.org/artificial-intelligence/ [Useful AI]: https://usefulai.com/ diff --git a/knowledge base/ai/claude/claude code.md b/knowledge base/ai/claude/claude code.md index 8cb9232..6c976db 100644 --- a/knowledge base/ai/claude/claude code.md +++ b/knowledge base/ai/claude/claude code.md @@ -205,7 +205,7 @@ Manually add the MCP server definition to `$HOME/.claude.json`: Refer [Skills][documentation/skills]. -See also [create custom skills]. +See also [create custom skills] and [Prat011/awesome-llm-skills]. Skills superseded commands.
Existing `.claude/commands/` files will currently still work, but skills with the same name will take precedence. @@ -307,6 +307,7 @@ Claude Code version: `v2.1.41`.
- [Claude Code router] - [Gemini CLI] - [OpenCode] +- [Prat011/awesome-llm-skills] ### Sources @@ -339,3 +340,4 @@ Claude Code version: `v2.1.41`.
[AWS API MCP Server]: https://github.com/awslabs/mcp/tree/main/src/aws-api-mcp-server [Cost Explorer MCP Server]: https://github.com/awslabs/mcp/tree/main/src/cost-explorer-mcp-server [pffigueiredo/claude-code-sheet.md]: https://gist.github.com/pffigueiredo/252bac8c731f7e8a2fc268c8a965a963 +[Prat011/awesome-llm-skills]: https://github.com/Prat011/awesome-llm-skills diff --git a/knowledge base/ai/ml.md b/knowledge base/ai/ml.md new file mode 100644 index 0000000..b6dea51 --- /dev/null +++ b/knowledge base/ai/ml.md @@ -0,0 +1,102 @@ +# Machine learning + +Branch of [AI] focusing on developing models and algorithms that can learn patterns from data without being explicitly +programmed for every task, and subsequently make accurate inferences about new data. + +It is a pattern recognition ability that enables models to make decisions or predictions without explicit, hard-coded +instructions. + + + +1. [TL;DR](#tldr) +1. [Further readings](#further-readings) + 1. [Sources](#sources) + +## TL;DR + +All machine learning is AI, but not all AI is machine learning. + +Rules-based models become increasingly brittle the more data is added to them.
+They require accurate, universal criteria to define the results they need to achieve. This is not scalable. + +ML models operate by a logic that is learned through experience, and not explicitly programmed into them.
+They train by analyzing data and predicting the next result; prediction errors are calculated, and the algorithm is +adjusted to reduce the possibility of errors.
+The training process is repeated until the model is accurate. + +ML works through mathematical logic. Relevant characteristics (A.K.A. _features_) of each data point **must** be +expressed numerically, so that the data can be fed into the mathematical algorithm that will _learn_ to map a given +input to the desired output. + +ML is mainly divided into the following types: + +- _Supervised_ learning. + + Models learn from _labelled_ data. Every input has a corresponding _correct_ output.
+ Models make predictions, compare those with the true outputs, and adjust themselves to reduce errors and improve + accuracy over time.
+ The goal is to train to make accurate predictions on new, unseen data. + +- _Unsupervised_ learning. + + Models work **without** labelled data.
+ They learn patterns on their own by grouping similar data points or finding hidden structures without human + intervention.
+ Helps identify hidden patterns in data. Useful for grouping, compression and anomaly detection.
+ Used for tasks like clustering, dimensionality reduction and Association Rule Learning. + +- _Reinforcement_ learning. + + Teaches agents to make decisions through trial and error to maximize cumulative rewards.
+ Allows machines to learn by interacting with an environment and receiving feedback based on their actions. This + feedback comes in the form of rewards or penalties.
+ Agents use the feedback to optimize their decision-making over time. + +- _Semi-supervised_ learning. + + Hybrid machine learning approach using both supervised and unsupervised learning.
+ Uses a small amount of labelled data, combined with a large amount of unlabelled data to train models.
+ The goal is to learn a function that accurately predicts outputs based on inputs, like with supervised learning, but + with much less labelled data.
+ Particularly valuable when acquiring labelled data is expensive or time-consuming, yet unlabelled data is plentiful + and easy to collect. + +- _Self-supervised_ learning. + + Subset of unsupervised learning.
+ Models train using data that does not have any labels or answers provided. Instead of needing people to label the + data, the models themselves find patterns and create their own labels from the data automatically.
+ Especially useful when there is a lot of data, but only a small part of it is labelled or labelling the data would + take a lot of time and effort. + +_Deep learning_ has emerged as the state-of-the-art AI model architecture across nearly every domain.
+It relies on distributed _networks_ of mathematical operations providing the ability to learn intricate nuances of very +complex data.
+It requires very large amounts of data and computational resources. + +## Further readings + +### Sources + +- geeksforgeeks.com's [Machine Learning Tutorial][geeksforgeeks / machine learning tutorial] +- IBM's [What is machine learning?][ibm / what is machine learning?] +- Oracle's [What is machine learning?][oracle / what is machine learning?] +- [Machine learning, explained] + + + + + +[AI]: README.md + + + + +[geeksforgeeks / Machine Learning Tutorial]: https://www.geeksforgeeks.org/machine-learning/ +[IBM / What is machine learning?]: https://www.ibm.com/think/topics/machine-learning +[Oracle / What is machine learning?]: https://www.oracle.com/artificial-intelligence/machine-learning/what-is-machine-learning/ +[Machine learning, explained]: https://mitsloan.mit.edu/ideas-made-to-matter/machine-learning-explained