Deep learning (also known as deep structured learning or hierarchical learning) is part of a broader family of machine learning methods based on artificial neural networks. Learning can be supervised, semi-supervised or unsupervised. Deep learning architectures such as deep neural networks, deep belief networks, recurrent neural networks and con…

Hierarchical Actor-Critic in Pytorch

Introduction to part-of-speech tagging and shallow parsing with keras

Modularity-based graph population integration

This is the repository for the paper Hierarchical Quality-Diversity for Online Damage Recovery which was accepted at GECCO 2022.

Reverse Curriculum Vicinity Learning: Reinforcement Hierarchical algorithm for solving complex RL tasks.

Companion code repository to Marcou et al. 2024, Creating a computer assisted ICD coding system: Performance metric choice and use of the ICD hierarchy

[IJCV] PointSegBase: a codebase for point cloud segmentation research. Related works: Deep Hierarchical Learning for 3D Semantic Segmentation

This is a repository for paper "Towards Data-driven Design of Asymmetric Hydrogenation of Olefins: Database and Hierarchical Learning".

Multi-scale molecular toxicity prediction using hierarchical graph neural networks with adaptive curriculum learning that prioritizes structurally complex molecules during training. Introduces a novel dual-granularity message passing mechanism (atom-level and functional-group-level) combined with difficulty-aware sample weighting based on molecular

A PyTorch implementation combining temporal attention mechanisms with hierarchical forecast reconciliation for multi-level retail sales prediction. The key innovation is learnable reconciliation matrices that replace traditional bottom-up/top-down aggregation with differentiable neural projections, ensuring probabilistic coherence across 4 hierarch

Question answering system for SQuAD 2.0 combining hierarchical span prediction, supervised contrastive learning, and adversarial training with synergistic component integration.

A novel framework for chest X-ray diagnosis that explicitly models aleatoric uncertainty through credal set theory. Combines hierarchical multi-label classification with dynamic label smoothing calibrated by radiologist uncertainty annotations, implementing evidential deep learning to learn prediction sets instead of point estimates.

Multi-timescale affective agents with theatrical control - 97K parameter architecture exploring functional correlates of consciousness

An automated practice system for mastering complex skills