mbax9an4 / Paper_summaries

Key ideas and contributions of papers I've read.

Deep Learning Regularization Methods:

• Batch Normalization
• Supervised autoencoders: Improving generalization performance with unsupervised regularizers

Training Spiking Neural Networks

• Unsupervised Learning of Digit Recognition using Spike-Timing-Dependent Plasticity
• Deep Learning in Spiking Neural Networks
• Hybrid Macro/Micro Level Backpropagation for Training Deep Spiking Neural Networks
• Spike-Train Level Backpropagation for Training Deep Recurrent Spiking Neural Networks
• SLAYER: Spike Layer Error Reassignment in Time

Ensembles of Spiking Neural Networks

• STDP-Based Unsupervised Multimodal Learning With Cross-Modal Processing in Spiking Neural Network
• Wide Learning
• EnsembleSNN: Distributed Assistive STDP Leanring for Energy-Efficient Recognition in Spiking Neural Networks
• Unsupervised Learning in an Ensemble of Spiking Neural Networks Mediated by ITDP
• SpiLinC: Spiking Liquid-Ensemble Computing for Unsupervised Speech and Image Recognition

Ensemble learning theory

• "Good" and "Bad" Diversity in Majority Vote Ensembles
• Critic Driven Ensemble Classification
• Measures of Diversity in Classifier Ensembles and Their Relationship with the Ensemble Accuracy
• Neural Network Ensembles, Cross Validation, and Active Learning
• Selecting Weighting Factors in Logarithmic Opinion Pools
• Neural Network Ensembles

Supervised Learning theory

• Neural Networks and the Bias-Variance Dilemma

Neural network architectures

• Powerful, transferable representations for molecules through intelligent task selection in deep multitask networks

Representation learning

• TASK2VEC: Task Embedding for Meta-Learning