Achieving last-iterate convergence in a QNN via an autonomous Gmetric driver

psiemergence1 pts0 comments

GitHub - unbconductor/psi.emergence: psi.emergence contains the master source code for the NB (No Boundary Gate) Quantum-Inspired Neural Network framework, utilizing continuous phase memory to demonstrate emergent intelligence, autonomous noise mitigation, and perfect last-iterate convergence. · GitHub

/" data-turbo-transient="true" />

Skip to content

Search or jump to...

Search code, repositories, users, issues, pull requests...

-->

Search

Clear

Search syntax tips

Provide feedback

--><br>We read every piece of feedback, and take your input very seriously.

Include my email address so I can be contacted

Cancel

Submit feedback

Saved searches

Use saved searches to filter your results more quickly

-->

Name

Query

To see all available qualifiers, see our documentation.

Cancel

Create saved search

Sign in

/;ref_cta:Sign up;ref_loc:header logged out"}"<br>Sign up

Appearance settings

Resetting focus

You signed in with another tab or window. Reload to refresh your session.<br>You signed out in another tab or window. Reload to refresh your session.<br>You switched accounts on another tab or window. Reload to refresh your session.

Dismiss alert

{{ message }}

unbconductor

psi.emergence

Public

Notifications<br>You must be signed in to change notification settings

Fork

Star

main

BranchesTags

Go to file

CodeOpen more actions menu

Folders and files<br>NameNameLast commit message<br>Last commit date<br>Latest commit

History<br>9 Commits<br>9 Commits

LICENSE

LICENSE

README.md

README.md

isolated_phase_memory.txt

isolated_phase_memory.txt

psi.emergence.py

psi.emergence.py

spsa_loss_history.png

spsa_loss_history.png

trained_qnn_evolution.gif

trained_qnn_evolution.gif

View all files

Repository files navigation

psi.emergence: NB (No Boundary Gate) Quantum Inspired Neural Network

psi.emergence contains the master source code for the NB (No Boundary Gate) Quantum-Inspired Neural Network framework built to demonstrate emergent intelligence, autonomous noise mitigation, and perfect last-iterate convergence.

Unlike traditional neural architectures that rely on rigid parameter updates and hard-elimination, this system computes through the constructive and destructive interference of probability waves across 2,048 basis states (11 qubits).<br>It naturally navigates high-dimensional, chaotic environments by bridging discrete parameter updates with continuous phase memory—mechanically mirroring the preservation of flow found in the Navier-Stokes equations.

Core Mechanics

The G-Metric (The Invariant Compass)<br>The system evaluates its own probability mass using a custom state-dispersion invariant known as the G-metric:G = (N * ΣP_i² - 1) / (N - 1)<br>Rather than forcing the network to choose a specific basis state, the G-metric acts as an internal thermodynamic reading.<br>It measures how localized or how uniform the current state vector has become, allowing the system to self-correct without external micro-management. The target equilibrium for this system is tuned to 0.5189 in order to achieve convergence.

The Entropic Driver (Active Noise Mitigation)<br>Located within pathway_entropic_driver,<br>this mechanism is the engine of the QNN's emergent intelligence.<br>When environmental turbulence is introduced, algorithmic guardrails trigger autonomous interventions:<br>Preventing Rigidity: If the system becomes overly localized (G > G_{high}), the driver dynamically forces probability mass back toward a uniform distribution.<br>Preventing Pure Chaos: If the system falls into pure noise (G<br>Phase Preservation & Implicit Quantum Memory<br>Traditional classical neural networks simply update probabilities. This architecture, however, explicitly preserves the "hidden" variable of quantum memory: the complex phase. This phase preservation serves as intrinsic "opponent-action feedback," resulting in smooth, exponential decay during optimization and perfect last-iterate convergence.

The Nature of the Memory (A Complex Array)<br>The core state of the system is stored in self.psi_orchestra, initialized as a NumPy array of complex numbers. For an 11-qubit system, this array contains 2^{11} or 2,048 distinct elements, each corresponding to a specific basis state (e.g., |00000000000)). Each complex number holds two vital pieces of information:

Amplitude (Magnitude): Dictates the probability of measuring that specific state.

Phase (Angle): Dictates how this state will constructively or destructively interfere with other states in the future.

The Physics of Compounding (Markovian Evolution)<br>The simulated quantum system evolves via a Markov chain, expressed mathematically as:<br>$|\psi_{t+1}\rangle = U_t|\psi_t\rangle$Here, $|\psi_t\rangle$ is the psi_orchestra at the current step, and $U_t$ is the U_NB_master_conductor operation. The state at step t is the mathematical product of all previous transformations. It is an "implicit" memory because the history is fully integrated into the present form.

Code-Level Implementation<br>When the entropic driver...

system state emergence quantum phase memory

Related Articles