Towards Artificial Life
A Compositional, Biologically-Inspired Framework for Grounded Intelligence
Problem Statement
Today's AI, while powerful, is fundamentally limited. They are "word models," not "world models," lacking true understanding and grounding in physical reality.
Research Vision
My work is driven by a more ambitious goal: to understand the principles of life and consciousness, and to create truly autonomous systems that learn, adapt, and interact with the world. This presentation outlines my vision to contribute to the collective human effort of building systems that are not just intelligent, but in a meaningful sense, alive.
psychology Key Contribution
PAULA (Predictive Adaptive Unsupervised Learning Agent), a novel formal neuron model that combines graph-based architecture, vector-based communication, inherent metaplasticity, and prediction-driven learning—providing a biologically-inspired primitive for building grounded, world-modeling intelligence systems.
Research Highlights
Biologically-Grounded Principles
Moving away from standard backpropagation toward methods that better reflect natural neurodynamics.
Graph-Based Architecture
The neuron itself is a micro-graph, allowing for complex internal signal integration and meaningful propagation delays.
Temporal Dynamics
Information is represented not just in activation magnitude, but in the precise temporal evolution of spiking patterns, massively expanding the representational space.
Inherent Metaplasticity
Features context-dependent metaplasticity, where neuromodulatory signals can change the learning rules themselves in real-time.
Purely Local Learning
Synaptic updates rely solely on locally available pre- and post-synaptic activity, eliminating the need for biologically implausible global error signals.
Methodology
A Two-Pronged Approach to Building a Brain
A key direction in AI research is the move towards "object-centered physical models," a view I share. The question is how to derive them. My research investigates a complementary, bottom-up path to this goal.
Top-Down Goal
The "What": An agent with a high-level architecture for intelligence.
- Modality-Agnostic Core
- Active Feedback & Continuous Learning
- Hierarchy of "Supervisors" for self-awareness
Bottom-Up Primitive
The "How": An atom of intelligence inspired by biology.
- Formal Neuron Model
- Rich Dynamical System
- Emergent Learning & Representation
Converging on: Grounded Intelligence & World Models
A Point of Synergy
These are not conflicting views, but complementary levels of abstraction. My hypothesis is that a network of powerful, bottom-up units will, through learning, discover and form the very top-down, object-centered representations we seek. It's an investigation into how a world model might emerge.
The Atom of Intelligence
PAULA: The Formal Neuron Model
PAULA (Predictive Adaptive Unsupervised Learning Agent) is a departure from traditional ANNs, designed to support the core principles with a richer set of computational capabilities.
Graph-Based Architecture
The neuron itself is a micro-graph, allowing for complex internal signal integration and meaningful propagation delays.
Vector-Based Communication
Synapses transmit rich, multi-dimensional vectors, not just single weights, enabling more expressive communication.
Inherent Metaplasticity
Features context-dependent metaplasticity, where neuromodulatory signals can change the learning rules themselves in real-time.
Prediction as a Driving Force
Learning rules are based on temporal prediction, constantly striving to match incoming signals with the neuron's own state.
The Path Forward
A Phased Research Roadmap
A clear, methodical plan from foundational validation to long-term hardware co-design.
Current Status: The underlying mathematical model has been validated with breakthrough results and emergent phenomena observed. A comprehensive formal model implementation in Python has been developed, with extensive experimentation revealing powerful computational capabilities and inherent robustness. The complete implementation is available as an open-source framework for neural experimentation.