Artificial Neural Networks and Machine Learning - ICANN 2020

Model Compression I .- Fine-grained Channel Pruning for Deep Residual Neural Networks.- A Lightweight Fully Convolutional Neural Network of High Accuracy Surface Defect Detection.- Detecting Uncertain BNN Outputs on FPGA Using Monte Carlo Dropout Sampling.- Neural network compression via learnable wavelet transforms.- Fast and Robust Compression of Deep Convolutional Neural Networks.- Model Compression II .- Pruning artificial neural networks: a way to find well-generalizing, high-entropy sharp minima.- Log-Nets: Logarithmic Feature-Product Layers Yield More Compact Networks.- Tuning Deep Neural Network's hyperparameters constrained to deployability on tiny systems.- Obstacles to Depth Compression of Neural Networks.- Multi-task and Multi-label Learning .- Multi-Label Quadruplet Dictionary Learning.- Pareto Multi-Task Deep Learning.- Convex Graph Laplacian Multi-Task Learning SVM.- Neural Network Theory and Information Theoretic Learning .- Prediction Stabilityas a Criterion in Active Learning.- Neural Spectrum Alignment: Empirical Study.- Nonlinear, Nonequilibrium Landscape Approach to Neural Network Dynamics.- Hopfield Networks for Vector Quantization.- Prototype-Based Online Learning on Homogeneously Labeled Streaming Data.- Normalization and Regularization Methods .- Neural Network Training with Safe Regularization in the Null Space of Batch Activations.- The Effect of Batch Normalization in the Symmetric Phase.- Regularized Pooling.- Reinforcement Learning I .- Deep Recurrent Deterministic Policy Gradient for Physical Control.- Exploration via Progress-Driven Intrinsic Rewards.- An improved reinforcement learning based heuristic dynamic programming algorithm for model-free optimal control.- PBCS: Efficient Exploration and Exploitation Using a Synergy between Reinforcement Learning and Motion Planning.- Understanding failures of deterministic actor-critic with continuous action spaces and sparse rewards.- Reinforcement Learning II .- GAN-based Planning Model in Deep Reinforcement Learning.- Guided Reinforcement Learning via Sequence Learning.- Neural Machine Translation based on Improved Actor-Critic Method.- Neural Machine Translation based on Prioritized Experience Replay.- Improving Multi-Agent Reinforcement Learning with Imperfect Human Knowledge.- Reinforcement Learning III .- Adaptive Skill Acquisition in Hierarchical Reinforcement Learning.- Social Navigation with Human Empowerment driven Deep Reinforcement Learning.- Curious Hierarchical Actor-Critic Reinforcement Learning.- Policy Entropy for Out-of-Distribution Classification.- Reservoir Computing .- Analysis of reservoir structure contributing to robustness against structural failure of Liquid State Machine.- Quantifying robustness and capacity of reservoir computers with consistency profiles.- Two-Step FORCE Learning Algorithm for Fast Convergence in Reservoir Computing.- Morphological Computation of Skin Focusing on Fingerprint Structure.- Time Series Clustering with Deep Reservoir Computing.- ReservoirPy: an Efficient and User-Friendly Library to Design Echo State Networks.- Robotics and Neural Models of Perception and Action .- Adaptive, Neural Robot Control - Path Planning on 3D Spiking Neural Networks.- CABIN: A Novel Cooperative Attention Based Location Prediction Network Using Internal-External Trajectory Dependencies.- Neuro-Genetic Visuomotor Architecture for Robotic Grasping.- From Geometries to Contact Graphs.- Sentiment Classification .- Structural Position Network for Aspect-based Sentiment Classification.- Cross-Domain Sentiment Classification using Topic Attention and Dual-Task Adversarial Training.- Data Augmentation for Sentiment Analysis in English - the Online Approach.- Spiking Neural Networks I .- Dendritic computation in a point neuron model..- Benchmarking Deep Spiking Neural Networks on Neuromorphic Hardware.- Unsupervised Learning of Spatio-Temporal Receptive Fields from an Event-Based Vision Sensor.- Spike-Train Level Unsupervised Learning Algorithm for Deep Spiking Belief Networks.- Spiking Neural Networks II .- Modelling Neuromodulated Information Flow and Energetic Consumption at Thalamic Relay Synapses.- Learning Precise Spike Timings with Eligibility Traces.- Meta-STDP rule stabilizes synaptic weights under in vivo-like ongoing spontaneous activity in a computational model of CA1 pyramidal cell.- Adaptive Chemotaxis for improved Contour Tracking using Spiking Neural Networks.- Text Understanding I .- Mental Imagery-Driven Neural Network to Enhance Representation for Implicit Discourse Relation Recognition.- Adaptive Convolution Kernel for Text Classification via Multi-Channel Representations.- Text generation in discrete space.- Short text processing for analyzing user portraits: A dynamic combination.- Text Understanding II .- A Hierarchical Fine-Tuning Approach Based on Joint Embedding of Words and Parent Categories forHierarchical Multi-label Text Classification.- Boosting Tricks for Word Mover's Distance.- Embedding Compression with Right Triangle Similarity Transformations.- Neural Networks for Detecting Irrelevant Questions during Visual Question Answering.- F-Measure Optimisation and Label Regularisation for Energy-based Neural Dialogue State Tracking Models.- Unsupervised Learning .- Unsupervised Change Detection using Joint Autoencoders for Age-Related Macular Degeneration Progression.- A fast algorithm to find Best Matching Units in Self-Organizing Maps.- Tumor Characterization using Unsupervised Learning of Mathematical Relations within Breast Cancer Data.- Balanced SAM-kNN: Online Learning with Heterogeneous Drift and Imbalanced Data.- A Rigorous Link Between Self-Organizing Maps and Gaussian Mixture Models.- Collaborative Clustering through Optimal Transport.