Vasan Iyer

Aerospace/Embedded/AI engineer, Nano, ex-@DLR_en. Focus: UAV-GNC, Embedded Sw/Hw, C/C++, Python, FPGAs, Sensor Fusion, Computer Vision, ML/DL/RL. 4 Masters +PhD

[Vasan Iyer @iyer_vasan]

I engineer systems where advanced hardware physics meets real-time intelligent software. 🛰️💻🧠Backed by a PhD track & 4 specialized Master's degrees, I map complex mathematics into deterministic, bare-metal production code.Below is a breakdown of my engineering focus: 👇

[Antonio Lupetti @antoniolupetti]

"A Mathematical Explanation of Transformers" is a recent paper that develops a rigorous mathematical framework for understanding the architecture behind Transformers and large language models.

It interprets the Transformer as a discretization of a continuous integro-differential equation, with self-attention represented as a non-local integral operator, layer normalization as a projection onto a constrained set, and feedforward layers and activation functions incorporated into the same mathematical framework, then uses operator splitting and numerical discretization to recover the standard Transformer architecture and extend the formulation to multi-head attention, Vision Transformers, and convolutional Transformers.

I've already shared several resources on the mathematics behind neural networks, Transformers, and LLMs, but there always seems to be something new and interesting to explore in this area.

https://t.co/18IZwRRDZS

[Neo Kim @systemdesignone]

If you want to get GOD-LEVEL with AI engineering, learn these 15 concepts (save now):

[Vasan Iyer @iyer_vasan]

https://t.co/I2PSMO7hY3

[Alexandre TL @AlexandreTL2]

So I have been busy these last few months! Happy to present : The Little Book of Reinforcement Learning

[𝐒𝐫𝐢𝐧𝐢𝐯𝐚𝐬𝐚 𝐑𝐚𝐠𝐡𝐚𝐯𝐚 ζ(1/2 + i σₙ )=0 @SrinivasR1729]

Here is a beautiful integral I worked on today. Just observe the different closed-forms of this integral
It looks complicated, but periodicity removes the distracting triple oscillation. Reflection symmetry simplifies the inverse-tangent terms, while a complex logarithm reveals the hidden factorization. A classical logarithmic cosine identity then gives an explicit algebraic closed form. The same approach also produces elegant binomial, gamma, and hypergeometric representations.

[Anatoli Kopadze @AnatoliKopadze]

instead of watching 2 hours of Netflix tonight, watch this Stanford lecture

it's the clearest explanation I've seen of how ChatGPT and Claude actually work

useful whether you've never touched AI in your life or have been using it every day for the past year

i took the key ideas and turned them into a practical guide on how to actually get 100% out of AI

you can find it below with ready-to-copy prompts and solutions

[Steven Brunton @eigensteve]

Free PDF of my new Optimization book:
https://t.co/2QQMQMJqr2

If you like it, check it out on Amazon or at Cambridge University Press!

Please leave a review and email me with any typos/corrections.

[Turing Post @TheTuringPost]

"Introduction to Machine Learning" by Laurent Younes

If you already know the core ML concepts, this textbook is a great next step to learn or refresh the math behind them.

It explains:

- optimization, SGD, and Adam
- bias–variance
- regression, SVMs, and kernels
- decision trees
- neural networks
- graphical and generative models
- clustering
- generalization bounds

Though it’s a math book, it still covers the key ML methods along the way.

[Vasan Iyer @iyer_vasan]

Telescopic...

[Vasan Iyer @iyer_vasan]

Check out my production-ready flight code and firmware nodes on GitHub: https://t.co/DZxMO3hzBt Let's connect! Academic publications can be tracked via my ORCID and Google Scholar profiles

[Vasan Iyer @iyer_vasan]

I engineer systems where advanced hardware physics meets real-time intelligent software. 🛰️💻🧠Backed by a PhD track & 4 specialized Master's degrees, I map complex mathematics into deterministic, bare-metal production code.Below is a breakdown of my engineering focus: 👇

[Vasan Iyer @iyer_vasan]

3/ Structural Energy Storage 🔋
Bridging materials science with flight vehicle efficiency. My doctoral research focuses on high-tensile multifunctional composites for ambient-temperature structural sodium-ion batteries and supercapacitors

[𝐒𝐫𝐢𝐧𝐢𝐯𝐚𝐬𝐚 𝐑𝐚𝐠𝐡𝐚𝐯𝐚 ζ(1/2 + i σₙ )=0 @SrinivasR1729]

For #Pi day. Here are some beautiful integrals that can produce (π/e)^n. They connect analysis and number theory, hinting at fresh routes toward proving irrationality.
#mathematics #piday

[vixhaℓ @TheVixhal]

https://t.co/8QMuGgh98i

[Vasan Iyer @iyer_vasan]

https://t.co/VKCNtLqgOB

[Vasan Iyer @iyer_vasan]

https://t.co/2LiRblHNZw

[Turing Post @TheTuringPost]

A free comprehensive textbook – Linear Algebra for Computer Vision, Robotics, and Machine Learning

Covers both, essential theory and computation:

- vector spaces, matrices, norms
- eigenvalues, SVD, numerical algorithms
- applications like PCA, graphs, wavelets, and 3D rotations

[Vasan Iyer @iyer_vasan]

Happy to share my new published paper (third and final paper of my PhD)
Fabrication and characterization of high-tensile-strength PEO–PVP blend-based multifunctional composites for sodium-ion structural batteries - now published in Materials Advances https://t.co/CLdBeyNWxJ