An educational crypto, finance, and AI vocabulary puzzle about cryptographic tools, budget concepts, neural network activations, and dataset annotations.
Blockchain Cryptography
Cryptographic primitives help blockchains verify data and authorize transactions.
Hash FunctionDigital SignaturePublic KeyMerkle Tree
- Hash Function: A hash function maps input data to a fixed-size output; cryptographic hash functions are designed to make reversal and collisions computationally difficult.
- Digital Signature: A digital signature lets others verify that a message was signed using the private key corresponding to a public key.
- Public Key: A public key is the shareable part of an asymmetric key pair, used to verify signatures in blockchain systems.
- Merkle Tree: A Merkle tree combines hashes in a tree structure, enabling compact proofs that data belongs to a larger set.
Budget Analysis
Budget analysis compares planned and actual results and examines how costs relate to output.
Fixed CostVariable CostBudget VarianceBreak-Even Point
- Fixed Cost: A fixed cost stays constant in total over a relevant activity range and time period.
- Variable Cost: A variable cost changes in total as the level of production or activity changes.
- Budget Variance: A budget variance is the difference between an actual financial result and its budgeted amount.
- Break-Even Point: The break-even point is the activity level at which total revenue equals total costs.
Activation Functions
Activation functions introduce nonlinear transformations that help neural networks represent complex patterns.
ReLUSigmoidTanhSoftmax
- ReLU: ReLU returns zero for negative inputs and the input itself for nonnegative inputs.
- Sigmoid: The logistic sigmoid maps a real-valued input to a value between zero and one.
- Tanh: The hyperbolic tangent maps a real-valued input to a value between minus one and one.
- Softmax: Softmax converts a vector of scores into positive values that sum to one by exponentiating and normalizing them.
Data Annotation
Annotations attach labels or structured information to raw data for machine learning tasks.
Class LabelBounding BoxSegmentation MaskEntity Span
- Class Label: A class label identifies the category assigned to an example in a classification dataset.
- Bounding Box: A bounding box marks an object location in an image using a rectangle.
- Segmentation Mask: A segmentation mask assigns labels to image pixels to identify regions or objects.
- Entity Span: An entity span identifies the start and end of text referring to a named entity, such as a person or organization.