# Human-Guided Learning of Column Networks: Augmenting Deep Learning with Advice

## TL;DR

This paper introduces Knowledge-augmented Column Networks that incorporate human advice to improve learning efficiency and effectiveness in structured, low-data, and noisy domains.

## Contribution

It presents a novel method of integrating human advice into Column Networks, enhancing their performance and convergence in challenging data scenarios.

## Key findings

- Improved performance over standard Column Networks.
- Faster convergence with human advice guidance.
- Effective in sparse and noisy data environments.

## Abstract

Recently, deep models have been successfully applied in several applications, especially with low-level representations. However, sparse, noisy samples and structured domains (with multiple objects and interactions) are some of the open challenges in most deep models. Column Networks, a deep architecture, can succinctly capture such domain structure and interactions, but may still be prone to sub-optimal learning from sparse and noisy samples. Inspired by the success of human-advice guided learning in AI, especially in data-scarce domains, we propose Knowledge-augmented Column Networks that leverage human advice/knowledge for better learning with noisy/sparse samples. Our experiments demonstrate that our approach leads to either superior overall performance or faster convergence (i.e., both effective and efficient).