Open Codes

Source code, trained models and data released by the AI-based X-ray Imaging System (AXIS) Lab at Rensselaer Polytechnic Institute.

Group by

2026

4 projects

2025

3 projects

ReLinear

IEEE Transactions on Neural Networks and Learning Systems 2025

On Expressivity and Trainability of Quadratic Networks

Theory showing why quadratic networks are more expressive than conventional ones, and ReLinear, a training strategy that keeps them from collapsing.

  • Quadratic neurons
  • Expressivity
  • Training stability
Code available GitHub

2024

2 projects

Flipover

Visual Computing for Industry, Biomedicine, and Art 2024

Flipover Outperforms Dropout in Deep Learning

A stronger form of dropout: instead of zeroing selected neurons, Flipover reverses their outputs with a negative multiplier during training.

  • Regularization
  • Dropout
  • Adversarial robustness
Code available GitHub

2023

2 projects

2022

7 projects

SPICE

IEEE Transactions on Image Processing 2022

SPICE: Semantic Pseudo-Labeling for Image Clustering

An image clustering framework that separates feature learning from a clustering head and trains it with semantics-aware pseudo-labels, without any annotation.

  • Image clustering
  • Self-supervised learning
  • Pseudo-labeling
Code available GitHub
SparseShortcutTopology

IEEE Transactions on Artificial Intelligence 2022

On a Sparse Shortcut Topology of Artificial Neural Networks

A sparse shortcut topology that makes a one-neuron-wide deep network a universal approximator and generalizes well in practice.

  • Network architecture
  • Shortcut connections
  • Universal approximation
Code available GitHub

2021

5 projects

Interpretability Survey

IEEE Transactions on Radiation and Plasma Medical Sciences 2021

On Interpretability of Artificial Neural Networks: A Survey

A survey that proposes a taxonomy of interpretability research for neural networks, with an independent evaluation of selected methods and a view on medical applications.

  • Interpretability
  • Survey
  • Explainable AI
Code available GitHub

2020

5 projects

Moral Decisions

Visual Computing for Industry, Biomedicine, and Art 2020

Modeling of Moral Decisions with Deep Learning

Neural networks learn group moral preferences in the autonomous-vehicle dilemma from observed decisions, and are compared with a hierarchical Bayesian model.

  • Machine ethics
  • Autonomous vehicles
  • Decision modeling
Partial release GitHub
Virtual Monoenergetic CT

Patterns 2020

Virtual Monoenergetic CT Imaging via Deep Learning

A residual network maps conventional single-spectrum CT images to virtual monoenergetic images, giving dual-energy-like information without a dual-energy scanner.

  • Spectral CT
  • Virtual monoenergetic imaging
  • Material decomposition
Code available GitHub

2018

2 projects