Humans have a remarkable capacity to understand the physical dynamics of objects in their environment, flexibly capturing complex structures and interactions at multiple levels of detail. Inspired by this ability, we propose a hierarchical particle-based object representation that covers a wide variety of types of three-dimensional objects, including both arbitrary rigid geometrical shapes and deformable materials. We then describe the Hierarchical Relation Network (HRN), an end-to-end differentiable neural network based on hierarchical graph convolution, that learns to predict physical dynamics in this representation. Compared to other neural network baselines, the HRN accurately handles complex collisions and nonrigid deformations, generating plausible dynamics predictions at long time scales in novel settings, and scaling to large scene configurations. These results demonstrate an architecture with the potential to form the basis of next-generation physics predictors for use in computer vision, robotics, and quantitative cognitive science.
CRAN；Université de Lorraine（洛林大学）；CNRS（法国国家科学研究中心）
Activation functions (AFs) are an important part of the design of neural networks (NNs), and their choice plays a predominant role in the performance of a NN. In this work, we are particularly interested in the estimation of flexible activation functions using tensor-based solutions, where the AFs are expressed as a weighted sum of predefined basis functions. To do so, we propose a new learning algorithm which solves a constrained coupled matrix-tensor factorization (CMTF) problem. This technique fuses the first and zeroth order information of the NN, where the first-order information is conta…
We introduce LL-RNNs (Log-Linear RNNs), an extension of Recurrent Neural Networks that replaces the softmax output layer by a log-linear output layer, of which the softmax is a special case. This conceptually simple move has two main advantages. First, it allows the learner to combat training data sparsity by allowing it to model words (or more generally, output symbols) as complex combinations of attributes without requiring that each combination is directly observed in the training data (as the softmax does). Second, it permits the inclusion of flexible prior knowledge in the form of a prior…
Tsinghua University（清华大学）；Peking University（北京大学）；Huilan Limited（慧联（北京）有限公司）；Beijing University of Posts and Telecommunications（北京邮电大学）
It has been shown that Chinese poems can be successfully generated by sequence-to-sequence neural models, particularly with the attention mechanism. A potential problem of this approach, however, is that neural models can only learn abstract rules, while poem generation is a highly creative process that involves not only rules but also innovations for which pure statistical models are not appropriate in principle. This work proposes a memory-augmented neural model for Chinese poem generation, where the neural model and the augmented memory work together to balance the requirements of linguisti…
Generalized Reduction to the Isotropy for Flexible Equivariant Neural Fields
Amsterdam Machine Learning Lab (AMLab), University of Amsterdam（阿姆斯特丹机器学习实验室（AMLab），阿姆斯特丹大学）；Department of Mathematics and Computer Science, Eindhoven University of Technology（数学与计算机科学系，埃因霍温理工大学）；Leiden Institute of Advanced Computer Science, Universiteit Leiden（莱顿高级计算机科学研究所，莱顿大学）
We compare the fast training and decoding speed of RETURNN of attention models for translation, due to fast CUDA LSTM kernels, and a fast pure TensorFlow beam search decoder. We show that a layer-wise pretraining scheme for recurrent attention models gives over 1% BLEU improvement absolute and it allows to train deeper recurrent encoder networks. Promising preliminary results on max. expected BLEU training are presented. We are able to train state-of-the-art models for translation and end-to-end models for speech recognition and show results on WMT 2017 and Switchboard. The flexibility of RETU…
Neural Combinatorial Optimization for Stochastic Flexible Job Shop Scheduling Problems
Eindhoven University of Technology（埃因霍温理工大学）；Eindhoven Artificial Intelligence Systems Institute（埃因霍温人工智能系统研究所）；Delmia R&D, Dassault Systèmes（达索系统Delmia研发部）
SnareNet: Flexible Repair Layers for Neural Networks with Hard Constraints
Department of Mathematics, Stanford University（斯坦福大学数学系）；Institute for Computational and Mathematical Engineering, Stanford University（斯坦福大学计算与数学工程研究所）；Department of Management Science and Engineering, Stanford University（斯坦福大学管理科学与工程系）
Modern deep neural network (DNN) models generally require a huge amount of weight and activation values to achieve good inference outcomes. Those data inevitably demand a massive off-chip memory capacity/bandwidth, and the situation gets even worse if they are represented in high-precision floating-point formats. Effort has been made for representing those data in different 8-bit floating-point formats, nevertheless, a notable accuracy loss is still unavoidable. In this paper we introduce an extremely flexible 8-bit floating-point (FFP8) format whose defining factors - the bit width of exponen…
This paper presents Systolic-CNN, an OpenCL-defined scalable, run-time-flexible FPGA accelerator architecture, optimized for accelerating the inference of various convolutional neural networks (CNNs) in multi-tenancy cloud/edge computing. The existing OpenCL-defined FPGA accelerators for CNN inference are insufficient due to limited flexibility for supporting multiple CNN models at run time and poor scalability resulting in underutilized FPGA resources and limited computational parallelism. Systolic-CNN adopts a highly pipelined and paralleled 1-D systolic array architecture, which efficiently…
Efficient and Flexible Neural Network Training through Layer-wise Feedback Propagation
Fraunhofer Heinrich Hertz Institute（弗劳恩霍夫海因里希·赫兹研究所）；Otto-von-Guericke University（奥托·冯·古里克大学）；Singapore Institute of Technology（新加坡理工大学）；Technische Universität Berlin（柏林工业大学）；BIFOLD – Berlin Institute for the Foundations of Learning and Data（柏林学习与数据基础研究所）；Technological University Dublin（都柏林理工大学）
Arizona State University（亚利桑那州立大学）；The University of Texas at Austin（德克萨斯大学奥斯汀分校）；Rensselaer Polytechnic Institute（伦斯勒理工学院）
Extracting spatial-temporal knowledge from data is useful in many applications. It is important that the obtained knowledge is human-interpretable and amenable to formal analysis. In this paper, we propose a method that trains neural networks to learn spatial-temporal properties in the form of weighted graph-based signal temporal logic (wGSTL) formulas. For learning wGSTL formulas, we introduce a flexible wGSTL formula structure in which the user's preference can be applied in the inferred wGSTL formulas. In the proposed framework, each neuron of the neural networks corresponds to a subformula…
Numerical simulations in climate, chemistry, or astrophysics are computationally too expensive for uncertainty quantification or parameter-exploration at high-resolution. Reduced-order or surrogate models are multiple orders of magnitude faster, but traditional surrogates are inflexible or inaccurate and pure machine learning (ML)-based surrogates too data-hungry. We propose a hybrid, flexible surrogate model that exploits known physics for simulating large-scale dynamics and limits learning to the hard-to-model term, which is called parametrization or closure and captures the effect of fine- …
ETH Zürich（苏黎世联邦理工学院）；University of Sussex（萨塞克斯大学）；Imperial College London（帝国理工学院）；University of Oxford（牛津大学）；University of Cambridge（剑桥大学）；The Alan Turing Institute（艾伦·图灵研究所）；Queen Mary University of London（伦敦玛丽女王大学）
Striking progress has recently been made in understanding human cognition by analyzing how its neuronal underpinnings are engaged in different modes of information processing. Specifically, neural information can be decomposed into synergistic, redundant, and unique features, with synergistic components being particularly aligned with complex cognition. However, two fundamental questions remain unanswered: (a) precisely how and why a cognitive system can become highly synergistic; and (b) how these informational states map onto artificial neural networks in various learning modes. To address t…
IT4Innovations, VŠB-Technical University of Ostrava（俄斯特拉发技术大学 IT4Innovations 中心）；University of Surrey（萨里大学）；Machine Intelligence Research Labs (MIR Labs)（机器智能研究实验室）
In this work, a computational intelligence (CI) technique named flexible neural tree (FNT) was developed to predict die filling performance of pharmaceutical granules and to identify significant die filling process variables. FNT resembles feedforward neural network, which creates a tree-like structure by using genetic programming. To improve accuracy, FNT parameters were optimized by using differential evolution algorithm. The performance of the FNT-based CI model was evaluated and compared with other CI techniques: multilayer perceptron, Gaussian process regression, and reduced error pruning…
RESCHED: Rethinking Flexible Job Shop Scheduling from a Transformer-based Architecture with Simplified States
School of Computing and Information Systems, Singapore Management University, Singapore（新加坡管理大学计算机与信息系）；College of Computing and Data Science, Nanyang Technological University, Singapore（南洋理工大学计算与数据科学学院）；Institute of Marine Science and Technology, Shandong University, China（山东大学海洋科学与技术研究院）
Massachusetts Institute of Technology（麻省理工学院）；Center for Brains, Minds and Machines（脑、心智与机器中心）
Many animals, and an increasing number of artificial agents, display sophisticated capabilities to perceive and manipulate objects. But human beings remain distinctive in their capacity for flexible, creative tool use -- using objects in new ways to act on the world, achieve a goal, or solve a problem. To study this type of general physical problem solving, we introduce the Virtual Tools game. In this game, people solve a large range of challenging physical puzzles in just a handful of attempts. We propose that the flexibility of human physical problem solving rests on an ability to imagine th…
Holographic near-eye displays offer unprecedented capabilities for virtual and augmented reality systems, including perceptually important focus cues. Although artificial intelligence--driven algorithms for computer-generated holography (CGH) have recently made much progress in improving the image quality and synthesis efficiency of holograms, these algorithms are not directly applicable to emerging phase-only spatial light modulators (SLM) that are extremely fast but offer phase control with very limited precision. The speed of these SLMs offers time multiplexing capabilities, essentially ena…
Neural network models generally involve two important components, i.e., network architecture and neuron model. Although there are abundant studies about network architectures, only a few neuron models have been developed, such as the MP neuron model developed in 1943 and the spiking neuron model developed in the 1950s. Recently, a new bio-plausible neuron model, Flexible Transmitter (FT) model, has been proposed. It exhibits promising behaviors, particularly on temporal-spatial signals, even when simply embedded into the common feedforward network architecture. This paper attempts to understan…
Cranfield University（克兰菲尔德大学）；University of Warwick（华威大学）；Alan Turing Institute（艾伦·图灵研究所）
Achieving transparency in black-box deep learning algorithms is still an open challenge. High dimensional features and decisions given by deep neural networks (NN) require new algorithms and methods to expose its mechanisms. Current state-of-the-art NN interpretation methods (e.g. Saliency maps, DeepLIFT, LIME, etc.) focus more on the direct relationship between NN outputs and inputs rather than the NN structure and operations itself. In current deep NN operations, there is uncertainty over the exact role played by neurons with fixed activation functions. In this paper, we achieve partially ex…
