Skip to content
Free standard shipping to supported destinations
Delta-Xi LogoDelta Xi
ShopOur storyLearnHelp
Learn
OverviewConcepts
Delta-Xi LogoDelta Xi

A place for good ideas, on a shirt or off the page.

Say hello

Explore

  • Shop all
  • Mathematics T-shirts
  • Accessories
  • Learn
  • Our story

Here to help

  • Contact
  • Size & care questions
  • Shipping & returns
  • Your orders
  • Track an order

Keep in touch

  • Instagram
  • Discord
  • Telegram
  • Affiliate programme

© 2026 Delta Xi. Prices in USD.

PrivacyTerms

Your cookie choices

Essential cookies keep your basket and sign-in working. Optional cookies help us understand visits and measure ads. Privacy details.

STEM Concepts

Follow an equation, work through an example, or check an assumption. Browse 69 concepts across mathematics, physics and computing.

All📐Mathematics(19)⚛️Physics(12)🔄Algorithms(7)🏗️Data Structures(8)🤖Machine Learning(10)🧠CS Theory(5)🖥️Systems(2)🌐Networking(3)⚙️Engineering(2)🧪Chemistry(1)
🤖

theory

Machine Learning

Attention Mechanism

Technique that allows models to focus on relevant parts of the input sequence.

View Explanation
🤖

algorithm

Machine Learning

Backpropagation

Algorithm for training neural networks by computing gradients through the chain rule.

View Explanation
🤖

theory

Machine Learning

Backtest leakage

When a historical test uses information unavailable at the time.

View Explanation
\theta := \theta - \alpha \nabla_\theta J(\theta)
Machine Learning

Gradient Descent Update

How neural networks learn by following the slope

View Explanation
J(\theta)=\frac{1}{2m}\sum_{i=1}^m (h_\theta(x^{(i)}) - y^{(i)})^2
Machine Learning

Mean Squared Error

The cost function for measuring prediction accuracy

View Explanation
🤖

theory

Machine Learning

Neural Network

Computing system inspired by biological neural networks, consisting of interconnected nodes.

View Explanation
\sigma(z)=\frac{1}{1+e^{-z}}
Machine Learning

Sigmoid Function

Squashes any value into the range (0, 1) for probability

View Explanation
\sigma(\mathbf{z})_j = \frac{e^{z_j}}{\sum_{k=1}^K e^{z_k}}
Machine Learning

Softmax Function

Convert scores into probability distributions

View Explanation
🤖

theory

Machine Learning

Transformer Architecture

Neural network architecture based on self-attention, powering modern LLMs.

View Explanation
🤖

algorithm

Machine Learning

Walk-forward validation

Train on the past, test on a later period, then move forward.

View Explanation