Crate eryon_actors 

eryon-actors

This crate works to establish a sound foundation for computational entities within the eryon framework.

Features

• neural: enables machine-learning capabilities for actors.

Re-exports

pub use super::Driver;

pub use super::RawDriver;

pub use super::TriadDriver;

pub use super::NeuralPlant;

pub use super::WolframPlant;

pub use super::ComputationalEngine;

pub use super::RawEngine;

pub use super::Operator;

pub use super::OperatorKind;

pub use super::context::*;

pub use super::wolfram::*;

pub use super::agent::*;

pub use super::observer::*;

Modules

apply

clip

codex

ctx

drivers

this module works to provide various drivers (a.k.a. plants) for each of the partitions (virtual nodes) within the substrate.

engine

This module works to implement various engines compatible with the Plant.

error

gradient

init

like

mask

norm

operators

This module focuses on implementing various operators for the VNode. Each operator is a specialized actor that can be used to perform specific tasks.

propagation

scalar

surface

This crate focuses on materializing the surface of the headspace. Each surface is a neural network that is dynamically configured using the vertices to define the input layer while the tonic or centroid defines the network’s output. The hidden layers essentially fill in the remaining space in-between the input and output layers, using barycentric coordinates as “goalposts” to guide the network’s learning process.

tensor

traits

this module defines the traits of the actors.

types

this module contains the various types implemented in-support of the actors

vnode

Virtual Node ([Vnode])

wnb

Structs

MetricPositionIter

An iterator over the variants of MetricPosition

NeuralController

A controller for the neural Turing machine

NeuralEngine

A Neural Turing Machine (NTM) is a type of recurrent neural network that can learn to perform algorithmic tasks by interacting with an external memory. The NTM consists of a controller network that interacts with a memory matrix using attention mechanisms. Internally, the controller is a shallow feed-forward neural network capable of processing encoded inputs and producing outputs that determine the next state, symbol, and direction of the machine.

NeuralFeatures

Plant

The term plant comes from control theory, denoting a fully-controlled dynamical system that exists within some environment in-which both are part of a larger universe. This definition aptly describes our efforts, as the plant is a fully-controlled entity modeled topologically as a 2-simplex, representing a “slice” of the tonnetz.

SnapshotBase

SurfaceModel

A multi-layer perceptron implementation

SurfaceNetwork

A neural network capable of dynamic configuration. Essentially, each network is designed to materialize the surface of a 2-simplex (triad) using barycentric coordinates to define three critical points. These critical points define the minimum number of hidden layers within the network and serve as goalposts that guide the learning process. The remaining points continue this trend, simply mapping each extra hidden layer to another position within space. The verticies of the simplex are used to inform the input layer and in finding the centroid of the facet. The centroid defines the output layer of the facet, serving as the final piece in a pseudo sink-source dyanamic.

VNode

This struct manifests the partitions automatically allocated by the runtime as virtualized workspaces responsible for maintaining their plant’s. Their capabilities are defined by the current operator, allowing a node to become an observer, agent, etc

VirtualMemoryAnalysis

Statistics about a memory optimization operation

Enums

ActorError

MetricPosition

Position in metric hierarchy

Traits

Actor

Actors represent different operational modes that a virtual node can adopt, each providing specialized behavior patterns and capabilities.

ActorExt

Alphabet

This trait is used define the symbols available to the engines

ApplyGradient

A trait declaring basic gradient-related routines for a neural network

ApplyGradientExt

This trait extends the ApplyGradient trait by allowing for momentum-based optimization

ArrayLike

Backward

Backward propagate a delta through the system;

Biased

Clip

A trait denoting objects capable of being clipped between some minimum and some maximum.

ClipMut

This trait enables tensor clipping; it is implemented for ArrayBase

Codex

Decode

Decode defines a standard interface for decoding data.

DefaultLike

DropOut

[Dropout] randomly zeroizes elements with a given probability (p).

Encode

Encode defines a standard interface for encoding data.

FillLike

Forward

This trait denotes entities capable of performing a single forward step

Gradient

The Gradient trait defines a common interface for all gradients

Init

A trait for creating custom initialization routines for models or other entities.

InitInplace

This trait enables models to implement custom, in-place initialization methods.

L1Norm

a trait for computing the L1 norm of a tensor or array

L2Norm

a trait for computing the L2 norm of a tensor or array

NdLike

Norm

The Norm trait serves as a unified interface for various normalization routnines. At the moment, the trait provides L1 and L2 techniques.

Numerical

Numerical is a trait for all numerical types; implements a number of core operations

OnesLike

RawStore

A basic trait denoting objects that can be used to hold other entities

Scalar

The Scalar trait extends the Numerical trait to include additional mathematical operations for the purpose of reducing the number of overall traits required to complete various machine-learning tasks.

SeqStore

Store

A trait that extends the RawStore with various creation routines, accessors, etc.

Tensor

Weighted

ZerosLike

Type Aliases

NeuralNode

a type alias denoting a VNode equipped with a NeuralPlant

Rulespace

A type alias denoting a set of rules for a UTM stored as a HashMap

Snapshot

a type alias for an owned SnapshotBase

SnapshotRef

a type alias for a borrowed SnapshotBase

StabilityPattern

A stability pattern represents an input emphasis configuration and its expected output

WolframNode

a type alias denoting a VNode equipped with a WolframPlant