vinsis's Avatar

vinsis

@vinsis

Math ∪ ML

9
Followers
25
Following
11
Posts
22.11.2024
Joined
Posts Following

Latest posts by vinsis @vinsis

Linear Algebra for Programmers Permutation matrices, doubly stochastic matrices, Sinkhorn distance. Learn Linear Algebra from scratch. Build a foundation for Machine Learning and other key technologies.

🧪 A deep dive into permutations and their connection with doubly stochastic matrices, matrix scaling and Sinkhorn distance: www.linearalgebraforprogrammers.com/series/permu...

26.06.2025 09:04 👍 0 🔁 0 💬 0 📌 0

Has it been suspended just for the day or for the next few days?

07.04.2025 04:35 👍 0 🔁 0 💬 1 📌 0
Preview
quickstart-resources/mcp-client-python/client.py at main · modelcontextprotocol/quickstart-resources A repository of servers and clients from the Model Context Protocol tutorials - modelcontextprotocol/quickstart-resources

I looked at how a client is created since it is the one interfacing with the model: github.com/modelcontext...

What's still unclear is how it is extensible to other models than Claude. I guess their MCP client definition would adhere to their own LLM's behavior.

04.04.2025 14:06 👍 0 🔁 0 💬 1 📌 0

Looked into it and it's a lot simpler than I imagined. MCP is built on top of the function api. They standardized the tools specification and usage, and created a closed loop system to continue the conversation with the LLM. This standardization also allows one to share their tools with anyone.

04.04.2025 14:03 👍 1 🔁 0 💬 1 📌 0

Is there any info available on how MCP Client interfaces with the ML model itself? As in how/when is the token prediction stopped/resumed to use an available tool, how are query and generation contexts updated etc (under the hood workings of `self.anthropic.messages.create` basically) etc

30.03.2025 14:08 👍 1 🔁 0 💬 1 📌 0
Continuous normalizing flows. Linear Algebra for Programmers Continuous normalizing flows.

Presenting a simpler derivation of the ODE governing the dynamics of Continuous Normalizing Flows along with a clear interpretation of the equation:

www.linearalgebraforprogrammers.com/blog/continu...

#linearalgebra #ode #math #ml 🧪

23.03.2025 10:58 👍 3 🔁 0 💬 0 📌 0
Nice Jacobians for normalizing flows. Linear Algebra for Programmers Nice Jacobians for normalizing flows.

Nice Jacobians for normalizing flows

www.linearalgebraforprogrammers.com/blog/jacobia...

A short overview of Jacobians with easy to calculate determinants used in normalizing flows

#linearalgebra #math #ml

06.03.2025 01:43 👍 0 🔁 0 💬 0 📌 0

A new series is up on LA for Programmers: Matrix Calculus and AutoDiff.

www.linearalgebraforprogrammers.com/series/matri...

#linearalgebra #math #autodiff

01.02.2025 07:58 👍 0 🔁 0 💬 0 📌 0
Three interpretations of matrix products | Hacker News

Three interpretations of matrix products

Hacker news: news.ycombinator.com/item?id=3947...

Link to article: www.linearalgebraforprogrammers.com/blog/matmul_...

The third interpretation is the least known for some reason.

#linearalgebra #math

16.12.2024 06:42 👍 2 🔁 0 💬 0 📌 0
Linear Algebra for Programmers Learn Linear Algebra from scratch. Build a foundation for Machine Learning and other key technologies.

The website www.linearalgebraforprogrammers.com is available in dark mode now.

#linearalgebra #math

15.12.2024 05:39 👍 1 🔁 0 💬 0 📌 0
Different ways to describe rotations in 2D, 3D and higher dimensional spaces

Different ways to describe rotations in 2D, 3D and higher dimensional spaces

A series on the different ways we understand and describe rotations (2D matrices → Quaternions → Clifford algebra → Lie algebra):

www.linearalgebraforprogrammers.com/series/rotat...

🧪

23.11.2024 08:43 👍 0 🔁 0 💬 0 📌 0