ModularBrainAgent / README.md
Almusawee's picture
Update README.md
fa888d5 verified
|
raw
history blame
3.9 kB
---
tags:
- brain-inspired
- spiking-neural-network
- biologically-plausible
- modular-architecture
- reinforcement-learning
- vision-language
- pytorch
- curriculum-learning
- cognitive-architecture
- artificial-general-intelligence
license: mit
datasets:
- mnist
- imdb
- synthetic-environment
language:
- en
library_name: transformers
widget:
- text: "The weather is nice today."
- text: "I feel curious about the stars."
model-index:
- name: ModularBrainAgent
results:
- task:
type: image-classification
name: Vision-based Classification
dataset:
type: mnist
name: MNIST
metrics:
- type: accuracy
value: 0.98
- task:
type: text-classification
name: Language Sentiment Analysis
dataset:
type: imdb
name: IMDb
metrics:
- type: accuracy
value: 0.91
- task:
type: reinforcement-learning
name: Curiosity-driven Exploration
dataset:
type: synthetic-environment
name: Synthetic Environment
metrics:
- type: cumulative_reward
value: 112.5
---
# 🧠 ModularBrainAgent: A Brain-Inspired Cognitive AI Model
ModularBrainAgent is a biologically plausible, spiking neural agent combining vision, language, and reinforcement learning in a single architecture. Inspired by human neurobiology, it implements eight neuron types and complex synaptic pathways, including excitatory, inhibitory, modulatory, bidirectional, feedback, lateral, and plastic connections.
It’s designed for researchers, neuroscientists, and AI developers exploring the frontier between brain science and general intelligence.
---
## 🧩 Model Architecture
- **Total Neurons**: 576
- **Neuron Types**: Interneurons, Excitatory, Inhibitory, Cholinergic, Dopaminergic, Serotonergic, Feedback, Plastic
- **Core Modules**:
- `SharedEncoder`: Multidimensional feature compressor
- `CNNVision`: Convolutional module for visual inputs
- `GRULanguage`: Recurrent module for sentence understanding
- `ReplayMemory` + `Curiosity` + `Entropy`: RL exploration engine
- `Task Heads`: Classifiers + Reinforcement actor-critic
---
## 🧠 Features
- 🪐 Multi-modal input support (Images, Language, Environment signals)
- 🔁 Hebbian + gradient learning
- ⚡ Spiking simulation for dynamic activity
- 🧠 Biologically-inspired synaptic dynamics
- 🧬 Curriculum learning and memory consolidation
- 🔍 Fully modular: plug-and-play layers
---
## 📊 Performance Summary
| Task | Dataset | Metric | Result |
|-----------------------|----------------------|-------------------|--------|
| Digit Recognition | MNIST | Accuracy | 98% |
| Sentiment Analysis | IMDb | Accuracy | 91% |
| Exploration Task | Synthetic GridWorld | Cumulative Reward | 112.5 |
---
## 💻 Training Data
- `MNIST`: Handwritten digit classification
- `IMDb`: Sentiment classification from text
- `Synthetic Grid Environment`: Exploration and navigation
---
## 🧪 Intended Uses
| Use Case | Description |
|-----------------------------|------------------------------------------------------------|
| Neuroscience AI Research | For brain-inspired network modeling |
| Cognitive Simulation | Test artificial memory, attention, curiosity |
| Multi-task Agent Prototyping| For language + vision + decision-making models |
| Educational Tool | Learn principles of bio-AI, spiking neurons, and RL |
---
## ⚠️ Limitations
- Currently trained on small-scale datasets
- Needs GPU/TPU for efficient inference
- Cognitive feedback not yet implemented for all pathways
- Limited real-world generalization until scaled
---
## 📂 Repository Structure