1
Building Machines that Learn and Think Like People
2
Relational Deep Reinforcement Learning
3
Graph networks as learnable physics engines for inference and control
4
Relational inductive bias for physical construction in humans and machines
5
MolGAN: An implicit generative model for small molecular graphs
6
Hyperbolic Attention Networks
7
Adversarial Attacks on Neural Networks for Graph Data
8
Deep Nets: What have They Ever Done for Vision?
9
Behavior Is Everything: Towards Representing Concepts with Sensorimotor Contingencies
10
Prefrontal cortex as a meta-reinforcement learning system
11
Iterative Visual Reasoning Beyond Convolutions
12
Attention Solves Your TSP
13
Inference in Probabilistic Graphical Models by Graph Neural Networks
14
Deep Models of Interactions Across Sets
15
Self-Attention with Relative Position Representations
16
NetGAN: Generating Graphs via Random Walks
17
Composable Planning with Attributes
18
GraphRNN: A Deep Generative Model for Graphs
19
Learning Deep Generative Models of Graphs
20
NerveNet: Learning Structured Policy with Graph Neural Networks
21
Relational Neural Expectation Maximization: Unsupervised Discovery of Objects and their Interactions
22
Can Neural Networks Understand Logical Entailment?
23
Compositional Attention Networks for Machine Reasoning
24
Neural Relational Inference for Interacting Systems
25
Learning to Search with MCTSnets
26
Learning a SAT Solver from Single-Bit Supervision
27
On the Generalization of Equivariance and Convolution in Neural Networks to the Action of Compact Groups
28
Tree-to-tree Neural Networks for Program Translation
29
High-Order Graph Convolutional Recurrent Neural Network: A Deep Learning Framework for Network-Scale Traffic Learning and Forecasting
30
From Skills to Symbols: Learning Symbolic Representations for Abstract High-Level Planning
31
Dynamic Graph CNN for Learning on Point Clouds
32
Innateness, AlphaZero, and Artificial Intelligence
33
Theoretical Impediments to Machine Learning With Seven Sparks from the Causal Revolution
34
Covariant Compositional Networks For Learning Graphs
35
Deep Learning: A Critical Appraisal
36
Relation Networks for Object Detection
37
Non-local Neural Networks
38
Learning Explanatory Rules from Noisy Data
39
Few-Shot Learning with Graph Neural Networks
40
Learning to Represent Programs with Graphs
41
Hierarchical Representations for Efficient Architecture Search
42
Still not systematic after all these years: On the compositional skills of sequence-to-sequence recurrent networks
43
TreeQN and ATreeC: Differentiable Tree Planning for Deep Reinforcement Learning
44
Graph Attention Networks
45
Semantic Code Repair using Neuro-Symbolic Transformation Networks
46
Dynamic Routing Between Capsules
47
Learning Graph Representations with Embedding Propagation
48
Action Schema Networks: Generalised Policies with Deep Learning
49
Answering Visual-Relational Queries in Web-Extracted Knowledge Graphs
50
Representation Learning for Visual-Relational Knowledge Graphs
51
Mind Games: Game Engines as an Architecture for Intuitive Physics
52
Learning model-based planning from scratch
53
graph2vec: Learning Distributed Representations of Graphs
54
Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting
55
A Note on Learning Algorithms for Quadratic Assignment with Graph Neural Networks
57
VAIN: Attentional Multi-agent Predictive Modeling
58
Knowledge Transfer for Out-of-Knowledge-Base Entities : A Graph Neural Network Approach
59
Schema Networks: Zero-shot Transfer with a Generative Causal Model of Intuitive Physics
60
Attention is All you Need
61
Inductive Representation Learning on Large Graphs
62
Visual Interaction Networks: Learning a Physics Simulator from Video
63
A simple neural network module for relational reasoning
64
Metacontrol for Adaptive Imagination-Based Optimization
65
Learning Combinatorial Optimization Algorithms over Graphs
66
Neural Message Passing for Quantum Chemistry
67
Failures of Gradient-Based Deep Learning
69
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
70
A Structured Self-attentive Sentence Embedding
71
Discovering objects and their relations from entangled scene representations
72
DeepStack: Expert-level artificial intelligence in heads-up no-limit poker
73
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
74
Interaction Networks for Learning about Objects, Relations and Physics
75
Neural Combinatorial Optimization with Reinforcement Learning
76
Geometric Deep Learning on Graphs and Manifolds Using Mixture Model CNNs
77
Geometric Deep Learning: Going beyond Euclidean data
78
Learning to reinforcement learn
79
Differentiable Programs with Neural Libraries
80
Modular Multitask Reinforcement Learning with Policy Sketches
81
A Compositional Object-Based Approach to Learning Physical Dynamics
82
Neuro-Symbolic Program Synthesis
83
Learning Continuous Semantic Representations of Symbolic Expressions
84
Learning Graphical State Transitions
85
Deep Amortized Inference for Probabilistic Programs
86
Hybrid computing using a neural network with dynamic external memory
87
Using Neural Network Formalism to Solve Multiple-Instance Problems
88
Towards Deep Symbolic Reinforcement Learning
89
Semi-Supervised Classification with Graph Convolutional Networks
91
node2vec: Scalable Feature Learning for Networks
92
Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering
93
subgraph2vec: Learning Distributed Representations of Rooted Sub-graphs from Large Graphs
94
Towards a Neural Statistician
95
Learning Multiagent Communication with Backpropagation
96
Learning to Communicate with Deep Multi-Agent Reinforcement Learning
97
Learning Convolutional Neural Networks for Graphs
98
Attend, Infer, Repeat: Fast Scene Understanding with Generative Models
99
Discriminative Embeddings of Latent Variable Models for Structured Data
100
Molecular graph convolutions: moving beyond fingerprints
101
Group Equivariant Convolutional Networks
102
Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning
103
Mastering the game of Go with deep neural networks and tree search
104
Human-level concept learning through probabilistic program induction
105
Neural Programmer-Interpreters
106
Neural Random Access Machines
107
Gated Graph Sequence Neural Networks
108
Neural Module Networks
109
Convolutional Networks on Graphs for Learning Molecular Fingerprints
110
Effective Approaches to Attention-based Neural Machine Translation
111
Deep Convolutional Networks on Graph-Structured Data
112
Learning to Transduce with Unbounded Memory
113
Transition-Based Dependency Parsing with Stack Long Short-Term Memory
114
Probabilistic machine learning and artificial intelligence
115
End-To-End Memory Networks
116
LINE: Large-scale Information Network Embedding
117
Inferring Algorithmic Patterns with Stack-Augmented Recurrent Nets
118
Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks
119
Human-level control through deep reinforcement learning
120
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
121
GloVe: Global Vectors for Word Representation
122
Sequence to Sequence Learning with Neural Networks
123
Neural Machine Translation by Jointly Learning to Align and Translate
124
Recurrent Models of Visual Attention
125
Concepts in a Probabilistic Language of Thought
126
Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation
127
Deep learning in neural networks: An overview
128
DeepWalk: online learning of social representations
129
Spectral Networks and Locally Connected Networks on Graphs
130
Translating Embeddings for Modeling Multi-relational Data
131
Simulation as an engine of physical scene understanding
132
Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank
133
Linguistic Regularities in Continuous Space Word Representations
134
How to Build a Brain: A Neural Architecture for Biological Cognition
135
ImageNet classification with deep convolutional neural networks
136
Semantic Compositionality through Recursive Matrix-Vector Spaces
137
Bayesian Nonparametrics
138
Semi-Supervised Recursive Autoencoders for Predicting Sentiment Distributions
139
Parsing Natural Scenes and Natural Language with Recursive Neural Networks
140
How to Grow a Mind: Statistics, Structure, and Abstraction
141
Weisfeiler-Lehman Graph Kernels
142
Probabilistic models of cognition: exploring representations and inductive biases
143
Probabilistic Graphical Models - Principles and Techniques
144
The discovery of structural form
145
Church: a language for generative models
146
Hierarchical models of behavior and prefrontal function
147
Five Rules for the Evolution of Cooperation
148
A simple rule for the evolution of cooperation on graphs and social networks
149
A new model for learning in graph domains
150
Graph neural networks for ranking Web pages
151
Introduction to real-time ray tracing
152
Reasoning about relations.
153
A symbolic-connectionist theory of relational inference and generalization.
154
Relational reinforcement learning
155
On Language: On the Diversity of Human Language Construction and Its Influence on the Mental Development of the Human Species
156
Holographic reduced representations
158
Neural Networks and the Bias/Variance Dilemma
159
Distributed representations, simple recurrent networks, and grammatical structure
160
Probabilistic reasoning in intelligent systems: Networks of plausible inference
161
Mapping Part-Whole Hierarchies into Connectionist Networks
162
Recursive Distributed Representations
163
Finding Structure in Time
164
Backpropagation Applied to Handwritten Zip Code Recognition
165
On language and connectionism: Analysis of a parallel distributed processing model of language acquisition
166
Connectionism and cognitive architecture: A critical analysis
167
Fusion, Propagation, and Structuring in Belief Networks
168
Acquisition of cognitive skill.
169
An interactive activation model of context effects in letter perception: I. An account of basic findings.
170
Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position
171
THE LANGUAGE OF THOUGHT
172
Forest before trees: The precedence of global features in visual perception
173
STRIPS: A New Approach to the Application of Theorem Proving to Problem Solving
174
PRINCIPLES OF NEURODYNAMICS. PERCEPTRONS AND THE THEORY OF BRAIN MECHANISMS
175
On the new Riddle of induction
176
The Nature of Explanation
177
Artificial Intelligence A Modern Approach 3rd Edition
178
Stretching beyond the specific
179
Learning to See Physics via Visual De-animation
181
Dropout: a simple way to prevent neural networks from overfitting
182
Computational Capabilities of Graph Neural Networks
183
The Graph Neural Network Model
184
The Need for Biases in Learning Generalizations
186
Introduction to Statistical Relational Learning
187
Causality : Models , Reasoning , and Inference
189
On language : on the diversity of human language construction and its influence on the mental development of the human species
190
Structure mapping in analogy and similarity.
191
Understanding normal and impaired word reading: computational principles in quasi-regular domains.
192
Tensor Product Variable Binding and the Representation of Symbolic Structures in Connectionist Systems
193
Artificial Intelligence , volume 46.
194
Principles of neurodynamics
196
The interaction of nature and nurture.
197
Opinion TRENDS in Cognitive Sciences Vol.10 No.7 July 2006 Special Issue: Probabilistic models of cognition Theory-based Bayesian models of inductive learning and reasoning
198
d master serves a roughly similar purpose to the GN’s u , but is defined as an extra node connected to all others, and thus does not influence the edge and global updates directly
199
φ u is applied once per graph, and computes an update for the global attribute, u (cid:48)
200
{ i } i =1: N 4. ρ e → u is applied to E (cid:48) , and aggregates all edge updates, into ¯e (cid:48)
