Improving machine learning algorithms via efficient data relevance discovery 

Generating gestures from speech for virtual humans using machine learning approaches 

Transfer learning for intelligent systems in the wild 

Learning shared subspaces across multiple views and modalities 

Sample-efficient and robust neurosymbolic learning from demonstrations 

Efficient graph processing with graph semantics aware intelligent storage 

Machine learning techniques for perceptual quality enhancement and semantic image segmentation 

Structure learning for manifolds and multivariate time series 

Local-aware deep learning: methodology and applications 

Beyond parallel data: decipherment for better quality machine translation 

Machine-learning approaches for modeling of complex materials and media 

Learning to diagnose from electronic health records data 

High-throughput methods for simulation and deep reinforcement learning 

Tensor learning for large-scale spatiotemporal analysis 

Scaling recommendation models with data-aware architectures and hardware efficient implementations 

Quickly solving new tasks, with meta-learning and without 

USC Computer Science Technical Reports, no. 867 (2005) 

Coding centric approaches for efficient, scalable, and privacy-preserving machine learning in large-scale distributed systems 

Mutual information estimation and its applications to machine learning 

Toward counteralgorithms: the contestation of interpretability in machine learning 

Development of data-driven user-centered building façade design guideline models: machine learning-based approaches to predict user preferences 

Learning distributed representations from network data and human navigation 

Word, sentence and knowledge graph embedding techniques: theory and performance evaluation 

Scalable exact inference in probabilistic graphical models on multi-core platforms 

Scalable sampling and reconstruction for graph signals