Adaptive Variational Memory Encoding for Recurrent Data Synthesis
ISEF · 2017 Robotics and Intelligent Machines
Overview
This work proposes a generative architecture that incorporates a natural approach to data synthesis. The Adaptive Variational Memory Encoding (AVME) model learns to represent data in an iterative manner during training, allowing for adaptive generation when sampling new data. One-shot approaches to data synthesis lack recurrent communication between dependencies during generation; this work attempts to lessen the likelihood of incoherent samples by giving the model time to iteratively update its output. Such a mechanism is largely inspired by the adaptive capabilities of the human mind for continuous predictive insight, resulting in a statistical model entwined with natural techniques. The AVME model is applied to both classical and conditional image generation, and shown to be effective at both tasks, achieving state of the art results on the MNIST dataset.
Competition history
- ISEF 2017
Resources
Related projects
ISEF · 2025
Symmetry-Preserving Variational Autoencoder and Latent Space Rectified Flow Diffusion for Accelerated Materials Discovery With Geometric Graph Neural Networks and Integrated Property Network Multi-Layer Perceptron
ISEF · 2022
Adaptive Learning: Evolving Explainable Predictions
ISEF · 2020
Memory-augmented Neural Agents for Deep Model-free Reinforcement Learning
ISEF · 2026
Integrating Vision-Language Models and Retrieval-Augmented Generation for Adaptive Alzheimer's Assistance
Closest projects by meaning, across every fair and year in the corpus.
Source: Regeneron International Science and Engineering Fair