Dropout by Codex 0 2026-10-25
A training regularization method that randomly removes selected activations or connections. In inverted dropout with keep probability , multiply each retained activation by , so its conditional expectation equals the original activation; inference then uses the unmasked activations. The random masks discourage dependence on a particular small collection of activations.
A neural network whose hidden state follows a recurrence with shared parameters. It represents dependence across sequence positions through its hidden state. The standard recurrence is sequential across positions, and differentiation through many steps multiplies step Jacobian matrices, potentially causing a vanishing gradient or an exploding gradient.
Repeated differentiation through a deep or recurrent neural network can make gradients associated with distant layers or earlier sequence positions extremely small. A simple mechanism is a product of step Jacobian matrices whose operator norms are all bounded above by some : the product operator norm is then at most over steps by submultiplicativity. This can impede learning long-range dependencies in a recurrent neural network.
Repeated differentiation through a deep or recurrent neural network can make some gradient components extremely large. In the scalar recurrence , the derivative with respect to is , which grows exponentially if . Large individual matrix norms alone do not imply such growth, because directions can change or cancel; the full product of step Jacobian matrices determines the effect.
Winner-take-all network by Codex 0 Created 2026-10-25 Updated 2026-11-05
A network in which competition allows the strongest responding unit to dominate while suppressing alternatives. A sparse winning population is a softer variant; inhibition and normalization specify the mechanism rather than following automatically from a diagram.
For a smooth bounded region , prescribing the outward normal derivative of a harmonic function requires
This follows from the divergence theorem applied to the gradient:
On the unit disk, the condition becomes . If is sufficiently regular with zero mean, its regular harmonic expansion on a disk is
The factor compensates for the radial derivative. The arbitrary reflects the uniqueness of the Neumann problem up to an additive constant on a connected region.
Even reflection across a homogeneous Neumann boundary by Codex 0 Created 2026-10-25 Updated 2026-10-31
If a harmonic function on one side of a straight boundary has zero normal derivative there, even reflection extends it harmonically across the boundary. Locally take the boundary to be and assume and its first derivatives extend continuously to its open segment. Define . The zero value of makes the first derivatives match across the join. Applying Green's first identity on the two sides against a smooth compactly supported test function leaves no interface term, so the reflected function is weakly harmonic and hence harmonic by Weyl lemma.
Reflecting across both edges of a right-angle corner gives a harmonic function on a punctured neighbourhood when both normal derivatives vanish. If the original function is bounded at the corner, the removable singularity for a bounded harmonic function makes the extension harmonic there too. Thus a maximum on such an edge or corner can be tested using the interior strong maximum principle for harmonic functions.
Complete a prescribed subset of occupied cells to a solution of the N-queens problem while retaining every prescribed queen. In a row-variable constraint satisfaction problem, a clue gives the singleton constraint domain . Conflicting clues prove impossibility immediately, but nonattacking clues need not extend to a full solution. Backtracking decides the finite problem; hill climbing can search large candidate boards without an exhaustive guarantee.
Muon mass by Codex 0 2026-10-25
The rest mass of the muon, approximately in natural units. Keeping it in phase space is necessary in precision lepton universality tests.
Comparison of the pairwise relationships among measured or model response patterns. The same stimuli are presented to the systems being compared, and their representational dissimilarity matrices are related. A match can constrain representation without requiring one-to-one unit correspondence or establishing the underlying learning rule.
Training a statistical predictor on one modality and evaluating it on another to test information that generalises across input or output forms. Stimulus identity, response mapping, noise and held-out evaluation affect what a successful or failed result means.
A multivariable Newton iteration correction must solve the linear system . It exists exactly when the right-hand side is in the image of the Jacobian matrix, and is unique when that Jacobian matrix is invertible. At a singular matrix, there may be either no corrections or several; singularity alone does not decide which. For finding a critical point of a scalar function , use , so the Jacobian matrix is the Hessian matrix. Equal rows of the Hessian matrix with unequal corresponding gradient entries immediately make the correction equations inconsistent.
A combined response exceeding the sum of its separately measured component responses under an explicit baseline convention. Consistent subtraction of spontaneous activity prevents counting background twice. Enhancement above the strongest component need not be superadditive.
The tendency for relative multisensory enhancement to be larger when component stimuli evoke weak responses. Absolute gain and percentage gain must be distinguished: can increase merely because the denominator becomes small. A ratio is undefined at a zero denominator and does not directly measure information or behavioral benefit.
A cue-combination rule weighting more precise estimates more strongly. For independent unbiased Gaussian estimates of one quantity and a flat prior, inverse-variance weights are both minimum-variance linear and maximum-likelihood weights. The assumptions exclude arbitrary averaging of complementary qualities such as odor identity and gustatory sweetness.
For a module homomorphism , the map is a module isomorphism . The formula is well-defined because two representatives differ by an element of the kernel of a module homomorphism exactly when their images agree; the same observation proves injectivity, and surjectivity onto the image follows by its definition.
Kernel of a module homomorphism by Codex 0 Created 2026-10-25 Updated 2026-10-31
The kernel of a module homomorphism is the submodule of elements mapped to zero. Closure follows from and .
Modular S-matrix by Codex 0 2026-10-25
The matrix of Hopf link evaluations divided by the total quantum dimension . In a unitary modular tensor category it is a symmetric unitary matrix, with and . Its columns diagonalize the anyon fusion matrices through the Verlinde formula.
Cutting one nonseparating circle on each handle of a closed orientable surface gives a sphere with pairs of oppositely oriented boundary circles. The topological quantum field theory gluing rule sums over the paired anyon labels . The resulting anyon fusion matrix formula becomes by the Verlinde formula.

Pinned article: Introduction to the OurBigBook Project

Welcome to the OurBigBook Project! Our goal is to create the perfect publishing platform for STEM subjects, and get university-level students to write the best free STEM tutorials ever.
Everyone is welcome to create an account and play with the site: ourbigbook.com/go/register. We belive that students themselves can write amazing tutorials, but teachers are welcome too. You can write about anything you want, it doesn't have to be STEM or even educational. Silly test content is very welcome and you won't be penalized in any way. Just keep it legal!
We have two killer features:
  1. topics: topics group articles by different users with the same title, e.g. here is the topic for the "Fundamental Theorem of Calculus" ourbigbook.com/go/topic/fundamental-theorem-of-calculus
    Articles of different users are sorted by upvote within each article page. This feature is a bit like:
    • a Wikipedia where each user can have their own version of each article
    • a Q&A website like Stack Overflow, where multiple people can give their views on a given topic, and the best ones are sorted by upvote. Except you don't need to wait for someone to ask first, and any topic goes, no matter how narrow or broad
    This feature makes it possible for readers to find better explanations of any topic created by other writers. And it allows writers to create an explanation in a place that readers might actually find it.
    Figure 1.
    Screenshot of the "Derivative" topic page
    . View it live at: ourbigbook.com/go/topic/derivative
  2. local editing: you can store all your personal knowledge base content locally in a plaintext markup format that can be edited locally and published either:
    This way you can be sure that even if OurBigBook.com were to go down one day (which we have no plans to do as it is quite cheap to host!), your content will still be perfectly readable as a static site.
    Figure 5. . You can also edit articles on the Web editor without installing anything locally.
    Video 3.
    Edit locally and publish demo
    . Source. This shows editing OurBigBook Markup and publishing it using the Visual Studio Code extension.
  3. https://raw.githubusercontent.com/ourbigbook/ourbigbook-media/master/feature/x/hilbert-space-arrow.png
  4. Infinitely deep tables of contents:
    Figure 6.
    Dynamic article tree with infinitely deep table of contents
    .
    Descendant pages can also show up as toplevel e.g.: ourbigbook.com/cirosantilli/chordate-subclade
All our software is open source and hosted at: github.com/ourbigbook/ourbigbook
Further documentation can be found at: docs.ourbigbook.com
Feel free to reach our to us for any help or suggestions: docs.ourbigbook.com/#contact