# UC Intel Final

## Docs

- [State Management API](https://mintlify.wiki/OverCV/UC-Intel-Final/api/components/state-management.md): Session state and workflow management for ML training pipelines
- [UI Components API](https://mintlify.wiki/OverCV/UC-Intel-Final/api/components/ui-components.md): Reusable Streamlit components for building ML training interfaces
- [Visualization API](https://mintlify.wiki/OverCV/UC-Intel-Final/api/components/visualization.md): Dataset visualization utilities for ML training dashboards
- [BaseModel](https://mintlify.wiki/OverCV/UC-Intel-Final/api/models/base.md): Abstract base class for all model implementations in UC Intel Final
- [CNNBuilder](https://mintlify.wiki/OverCV/UC-Intel-Final/api/models/cnn-builder.md): Build custom CNN architectures from layer stack configurations
- [Transfer Learning](https://mintlify.wiki/OverCV/UC-Intel-Final/api/models/transfer-learning.md): Fine-tune pre-trained models for image classification
- [Vision Transformers](https://mintlify.wiki/OverCV/UC-Intel-Final/api/models/transformers.md): Vision Transformer (ViT) implementation for image classification
- [Dataset](https://mintlify.wiki/OverCV/UC-Intel-Final/api/training/dataset.md): PyTorch Dataset and DataLoader utilities for malware image data
- [Training Engine](https://mintlify.wiki/OverCV/UC-Intel-Final/api/training/engine.md): Core training loop with callbacks, early stopping, and metrics tracking
- [Evaluator](https://mintlify.wiki/OverCV/UC-Intel-Final/api/training/evaluator.md): Test set evaluation and metrics computation
- [Optimizers](https://mintlify.wiki/OverCV/UC-Intel-Final/api/training/optimizers.md): Optimizer, scheduler, and loss function utilities
- [Transforms](https://mintlify.wiki/OverCV/UC-Intel-Final/api/training/transforms.md): Data augmentation and preprocessing transforms for malware images
- [System Architecture](https://mintlify.wiki/OverCV/UC-Intel-Final/concepts/architecture.md): Comprehensive overview of the UC Intel Final malware classification platform architecture
- [Model Architectures](https://mintlify.wiki/OverCV/UC-Intel-Final/concepts/models.md): Deep dive into available neural network architectures for malware classification
- [ML Workflow & Pipeline](https://mintlify.wiki/OverCV/UC-Intel-Final/concepts/workflow.md): End-to-end machine learning workflow from data preparation to model evaluation
- [Dataset Configuration](https://mintlify.wiki/OverCV/UC-Intel-Final/dashboard/dataset-config.md): Configure malware image datasets with splits, augmentation, and class balancing
- [Interpretability Tools](https://mintlify.wiki/OverCV/UC-Intel-Final/dashboard/interpretability.md): Visualize model attention with Grad-CAM, embeddings, and misclassification analysis
- [Model Builder](https://mintlify.wiki/OverCV/UC-Intel-Final/dashboard/model-builder.md): Design Custom CNN, Transformer, and Transfer Learning architectures for malware classification
- [Training Monitor](https://mintlify.wiki/OverCV/UC-Intel-Final/dashboard/monitoring.md): Compose experiments, start training, and monitor real-time progress
- [Dashboard Overview](https://mintlify.wiki/OverCV/UC-Intel-Final/dashboard/overview.md): Navigate the UC Intel Final Streamlit dashboard for malware classification
- [Results & Evaluation](https://mintlify.wiki/OverCV/UC-Intel-Final/dashboard/results.md): Analyze training curves, confusion matrices, and per-class performance metrics
- [Training Configuration](https://mintlify.wiki/OverCV/UC-Intel-Final/dashboard/training.md): Configure optimizers, learning rates, callbacks, and hyperparameters for model training
- [Installation](https://mintlify.wiki/OverCV/UC-Intel-Final/installation.md): Complete installation guide for the malware classification platform
- [Activation Map Visualization](https://mintlify.wiki/OverCV/UC-Intel-Final/interpretability/activation-maps.md): Visualize convolutional filter responses and understand hierarchical feature detection
- [Grad-CAM Visualization](https://mintlify.wiki/OverCV/UC-Intel-Final/interpretability/grad-cam.md): Understand what your model sees using Gradient-weighted Class Activation Mapping
- [t-SNE Feature Embeddings](https://mintlify.wiki/OverCV/UC-Intel-Final/interpretability/tsne.md): Visualize learned feature representations and analyze cluster quality in 2D space
- [Introduction](https://mintlify.wiki/OverCV/UC-Intel-Final/introduction.md): Advanced deep learning platform for malware image classification with PyTorch and Streamlit
- [Quick Start](https://mintlify.wiki/OverCV/UC-Intel-Final/quickstart.md): Get started with malware classification in 5 minutes
- [Conclusions & Findings](https://mintlify.wiki/OverCV/UC-Intel-Final/research/conclusions.md): Research conclusions, hypothesis verification, and future work recommendations
- [Experiments Conducted](https://mintlify.wiki/OverCV/UC-Intel-Final/research/experiments.md): Detailed experimental setup and configurations for hypothesis testing
- [Research Methodology](https://mintlify.wiki/OverCV/UC-Intel-Final/research/methodology.md): Detailed methodology for Deep Learning-based malware classification
- [Research Overview](https://mintlify.wiki/OverCV/UC-Intel-Final/research/overview.md): Automated malware family classification using Deep Learning - UC Intel Final Project
- [Research Results](https://mintlify.wiki/OverCV/UC-Intel-Final/research/results.md): Experimental results and performance analysis of malware classification models
- [Dataset Preparation](https://mintlify.wiki/OverCV/UC-Intel-Final/training/dataset-preparation.md): Learn how to prepare and augment datasets for training malware classification models
- [Model Evaluation](https://mintlify.wiki/OverCV/UC-Intel-Final/training/evaluation.md): Comprehensive guide to evaluating trained models and understanding performance metrics
- [Hyperparameter Tuning](https://mintlify.wiki/OverCV/UC-Intel-Final/training/hyperparameters.md): Comprehensive guide to optimizing training hyperparameters for best model performance
- [Model Selection](https://mintlify.wiki/OverCV/UC-Intel-Final/training/model-selection.md): Guide to choosing and configuring model architectures for malware classification