Meta-learning in neural networks: A survey
The field of meta-learning, or learning-to-learn, has seen a dramatic rise in interest in recent
years. Contrary to conventional approaches to AI where tasks are solved from scratch using …
years. Contrary to conventional approaches to AI where tasks are solved from scratch using …
Network pruning via performance maximization
Channel pruning is a class of powerful methods for model compression. When pruning a
neural network, it's ideal to obtain a sub-network with higher accuracy. However, a sub …
neural network, it's ideal to obtain a sub-network with higher accuracy. However, a sub …
Network intelligence in 6G: Challenges and opportunities
The success of the upcoming 6G systems will largely depend on the quality of the Network
Intelligence (NI) that will fully automate network management. Artificial Intelligence (AI) …
Intelligence (NI) that will fully automate network management. Artificial Intelligence (AI) …
Fasa: Feature augmentation and sampling adaptation for long-tailed instance segmentation
Recent methods for long-tailed instance segmentation still struggle on rare object classes
with few training data. We propose a simple yet effective method, Feature Augmentation and …
with few training data. We propose a simple yet effective method, Feature Augmentation and …
Meta-learning PINN loss functions
We propose a meta-learning technique for offline discovery of physics-informed neural
network (PINN) loss functions. We extend earlier works on meta-learning, and develop a …
network (PINN) loss functions. We extend earlier works on meta-learning, and develop a …
Is the most accurate ai the best teammate? optimizing ai for teamwork
AI practitioners typically strive to develop the most accurate systems, making an implicit
assumption that the AI system will function autonomously. However, in practice, AI systems …
assumption that the AI system will function autonomously. However, in practice, AI systems …
The worst of both worlds: A comparative analysis of errors in learning from data in psychology and machine learning
Arguments that machine learning (ML) is facing a reproducibility and replication crisis
suggest that some published claims in research cannot be taken at face value. Concerns …
suggest that some published claims in research cannot be taken at face value. Concerns …
Deep learning for in situ data compression of large turbulent flow simulations
As the size of turbulent flow simulations continues to grow, in situ data compression is
becoming increasingly important for visualization, analysis, and restart checkpointing. For …
becoming increasingly important for visualization, analysis, and restart checkpointing. For …
Customizing ML predictions for online algorithms
A popular line of recent research incorporates ML advice in the design of online algorithms
to improve their performance in typical instances. These papers treat the ML algorithm as a …
to improve their performance in typical instances. These papers treat the ML algorithm as a …
Softadapt: Techniques for adaptive loss weighting of neural networks with multi-part loss functions
AA Heydari, CA Thompson, A Mehmood - arXiv preprint arXiv:1912.12355, 2019 - arxiv.org
Adaptive loss function formulation is an active area of research and has gained a great deal
of popularity in recent years, following the success of deep learning. However, existing …
of popularity in recent years, following the success of deep learning. However, existing …