Adaptive Graph Fusion for Unsupervised Feature Selection -- Unsupervised Feature Selection via Local Total-order Preservation -- Discrete Stochastic Search and its Application to Feature-Selection for Deep Relational Machines -- Joint Dictionary Learning for Unsupervised Feature Selection -- Comparison between Filter Criteria for Feature Selection in Regression -- CancelOut: A layer for feature selection in deep neural networks -- Adaptive-L2 Batch Neural Gas -- Application of Self Organizing Map to Preprocessing Input Vectors for Convolutional Neural Network -- Hierarchical Reinforcement Learning with Unlimited Recursive Subroutine Calls -- Automatic Augmentation by Hill Climbing -- Learning Camera-invariant Representation for Person Re-identification -- PA-RetinaNet: Path Augmented RetinaNet for Dense Object Detection -- Singular Value Decomposition and Neural Networks -- PCI: Principal Component Initialization for Deep Autoencoders -- Improving Weight Initialization of ReLU and Output Layers -- Post-synaptic potential regularization has potential -- A Novel Modification on the Levenberg-Marquardt Algorithm for Avoiding Overfitting in Neural Network Training -- Sign Based Derivative Filtering for Stochastic Gradient Descent -- Architecture-aware Bayesian Optimization for Neural Network Tuning -- Non-Convergence and Limit Cycles in the Adam Optimizer -- Learning Internal Dense But External Sparse Structures of Deep Convolutional Neural Network -- Using feature entropy to guide filter pruning for efficient convolutional networks -- Simultaneously Learning Architectures and Features of Deep Neural Networks -- Learning Sparse Hidden States in Long Short-Term Memory -- Multi-objective Pruning for CNNs using Genetic Algorithm -- Dynamically Sacrificing Accuracy for Reduced Computation: Cascaded Inference Based on Softmax Confidence -- Light-Weight Edge Enhanced Network for On-orbit Semantic Segmentation -- Local Normalization Based BN Layer Pruning -- On Practical Approach to Uniform Quantization of Non-redundant Neural Networks -- Residual learning for FC kernels of convolutional network -- A Novel Neural Network-based Symbolic Regression Method: Neuro-Encoded Expression Programming -- Compute-efficient neural network architecture optimization by a genetic algorithm -- Controlling Model Complexity in Probabilistic Model-Based Dynamic Optimization of Neural Network Structures -- Predictive Uncertainty Estimation with Temporal Convolutional Networks for Dynamic Evolutionary Optimization -- Sparse Recurrent Mixture Density Networks for Forecasting High Variability Time Series with Confidence Estimates -- A multitask learning neural network for short-term traffic speed prediction and confidence estimation -- Central-diffused Instance Generation Method in Class Incremental Learning -- Marginal Replay vs Conditional Replay for Continual Learning -- Simplified computation and interpretation of Fisher matrices in incremental learning with deep neural networks -- Active Learning for Image Recognition using a Visualization-Based User Interface -- Basic Evaluation Scenarios for Incrementally Trained Classifiers -- Embedding Complexity of Learned Representations in Neural Networks -- Joint Metric Learning on Riemannian Manifold of Global Gaussian Distributions -- Multi-Task Sparse Regression Metric Learning for Heterogeneous Classification -- Fast Approximate Geodesics for Deep Generative Models -- Spatial Attention Network for Few-Shot Learning -- Routine Modeling with Time Series Metric Learning -- Leveraging Domain Knowledge for Reinforcement Learning using MMC Architectures -- Conditions for Unnecessary Logical Constraints in Kernel Machines -- HiSeqGAN: Hierarchical Sequence Synthesis and Prediction -- DeepEX: Bridging the Gap Between Knowledge and Data Driven Techniques for Time Series Forecasting -- Transferable Adversarial Cycle Alignment for Domain Adaption -- Evaluation of domain adaptation approaches for robust classification of heterogeneous biological data sets -- Named Entity Recognition for Chinese Social Media with Domain Adversarial Training and Language Modeling -- Deep Domain Knowledge Distillation for Person Re-identification -- A study on catastrophic forgetting in deep LSTM networks -- A Label-specific Attention-based Network with Regularized Loss for Multi-label Classification -- An Empirical Study of Multi-domain and Multi-task Learning in Chinese Named Entity Recognition -- Filter Method Ensemble with Neural Networks -- Dynamic Centroid Insertion and Adjustment for Data Sets with Multiple Imbalanced Classes -- Increasing the Generalisaton Capacity of Conditional VAEs -- Playing the Large Margin Preference Game.