Fully convolutional neural networks can process input of arbitrary size by applying a combination of downsampling and pooling. However, we find that fully convolutional image classifiers are not agnostic to the input size but rather show significant differences in performance: presenting the same image at different scales can result in different outcomes. A closer look reveals that there is no simple relationship between input size and model performance (no `bigger is better'), but that each each network has a preferred input size, for which it shows best results. We investigate this phenomenon by applying different methods, including spectral analysis of layer activations and probe classifiers, showing that there are characteristic features depending on the network architecture. From this we find that the size of discriminatory features is critically influencing how the inference process is distributed among the layers.
Accurate forecasts of fine particulate matter (PM 2.5) from wildfire smoke are crucial to safeguarding cardiopulmonary public health. Existing forecasting systems are trained on sparse and inaccurate ground truths, and do not take sufficient advantage of important spatial inductive biases. In this work, we present a convolutional neural network which preserves sparsity invariance throughout, and leverages multitask learning to perform dense forecasts of PM 2.5values. We demonstrate that our model outperforms two existing smoke forecasting systems during the 2018 and 2019 wildfire season in Bri…
The dominant paradigm in spatiotemporal action detection is to classify actions using spatiotemporal features learned by 2D or 3D Convolutional Networks. We argue that several actions are characterized by their context, such as relevant objects and actors present in the video. To this end, we introduce an architecture based on self-attention and Graph Convolutional Networks in order to model contextual cues, such as actor-actor and actor-object interactions, to improve human action detection in video. We are interested in achieving this in a weakly-supervised setting, i.e. using as less annota…
It has witnessed a growing demand for efficient representation learning on point clouds in many 3D computer vision applications. Behind the success story of convolutional neural networks (CNNs) is that the data (e.g., images) are Euclidean structured. However, point clouds are irregular and unordered. Various point neural networks have been developed with isotropic filters or using weighting matrices to overcome the structure inconsistency on point clouds. However, isotropic filters or weighting matrices limit the representation power. In this paper, we propose a permutable anisotropic convolu…
Carnegie Mellon University（卡内基梅隆大学）；Bosch Center for AI（博世人工智能中心）
Neural network weights are typically initialized at random from univariate distributions, controlling just the variance of individual weights even in highly-structured operations like convolutions. Recent ViT-inspired convolutional networks such as ConvMixer and ConvNeXt use large-kernel depthwise convolutions whose learned filters have notable structure; this presents an opportunity to study their empirical covariances. In this work, we first observe that such learned filters have highly-structured covariance matrices, and moreover, we find that covariances calculated from small networks may …
Fraunhofer Center for Machine Learning and SCAI（弗劳恩霍夫机器学习中心与SCAI）；University of Bonn（波恩大学）
The analysis of deforming 3D surface meshes is accelerated by autoencoders since the low-dimensional embeddings can be used to visualize underlying dynamics. But, state-of-the-art mesh convolutional autoencoders require a fixed connectivity of all input meshes handled by the autoencoder. This is due to either the use of spectral convolutional layers or mesh dependent pooling operations. Therefore, the types of datasets that one can study are limited and the learned knowledge cannot be transferred to other datasets that exhibit similar behavior. To address this, we transform the discretization …
University of Padova（帕多瓦大学）；University of Freiburg（弗赖堡大学）；University of Nottingham（诺丁汉大学）
Recently, many researchers have been focusing on the definition of neural networks for graphs. The basic component for many of these approaches remains the graph convolution idea proposed almost a decade ago. In this paper, we extend this basic component, following an intuition derived from the well-known convolutional filters over multi-dimensional tensors. In particular, we derive a simple, efficient and effective way to introduce a hyper-parameter on graph convolutions that influences the filter size, i.e. its receptive field over the considered graph. We show with experimental results on r…
Recent studies have shown that lung cancer screening using annual low-dose computed tomography (CT) reduces lung cancer mortality by 20% compared to traditional chest radiography. Therefore, CT lung screening has started to be used widely all across the world. However, analyzing these images is a serious burden for radiologists. The number of slices in a CT scan can be up to 600. Therefore, computer-aided-detection (CAD) systems are very important for faster and more accurate assessment of the data. In this study, we proposed a framework that analyzes CT lung screenings using convolutional neu…
In deep neural networks with convolutional layers, each layer typically has fixed-size/single-resolution receptive field (RF). Convolutional layers with a large RF capture global information from the input features, while layers with small RF size capture local details with high resolution from the input features. In this work, we introduce novel deep multi-resolution fully convolutional neural networks (MR-FCNN), where each layer has different RF sizes to extract multi-resolution features that capture the global and local details information from its input features. The proposed MR-FCNN is ap…
Reconstructing the local density field with combined convolutional and point cloud architecture
Ecole Polytechnique Rte de Saclay, 91120 Palaiseau, France（巴黎-萨克雷高等理工学院）；Center for Data-Driven Discovery Kavli IPMU, UTIAS, The University of Tokyo（数据驱动发现中心）；The University of Tokyo（东京大学）
Vrije Universiteit Amsterdam（阿姆斯特丹自由大学）；Delft University of Technology（代尔夫特理工大学）；University of Amsterdam（阿姆斯特丹大学）
When designing Convolutional Neural Networks (CNNs), one must select the size\break of the convolutional kernels before training. Recent works show CNNs benefit from different kernel sizes at different layers, but exploring all possible combinations is unfeasible in practice. A more efficient approach is to learn the kernel size during training. However, existing works that learn the kernel size have a limited bandwidth. These approaches scale kernels by dilation, and thus the detail they can describe is limited. In this work, we propose FlexConv, a novel convolutional operation with which hig…
The growing demand for the internet of things (IoT) makes it necessary to implement computer vision tasks such as object recognition in low-power devices. Convolutional neural networks (CNNs) are a potential approach for object recognition and detection. However, the convolutional layer in CNN consumes significant energy compared to the fully connected layers. To mitigate this problem, a new approach based on the Hadamard transformation as an alternative to the convolution operation is demonstrated using two fundamental datasets, MNIST and CIFAR10. The mathematical expression of the Hadamard m…
Convolutional layers in CNNs implement linear filters which decompose the input into different frequency bands. However, most modern architectures neglect standard principles of filter design when optimizing their model choices regarding the size and shape of the convolutional kernel. In this work, we consider the well-known problem of spectral leakage caused by windowing artifacts in filtering operations in the context of CNNs. We show that the small size of CNN kernels make them susceptible to spectral leakage, which may induce performance-degrading artifacts. To address this issue, we propo…
Machine-part interaction classification is a key capability required by Cyber-Physical Systems (CPS), a pivotal enabler of Smart Manufacturing (SM). While previous relevant studies on the subject have primarily focused on time series classification, change point detection is equally important because it provides temporal information on changes in behavior of the machine. In this work, we address point detection and time series classification for machine-part interactions with a deep Convolutional Neural Network (CNN) based framework. The CNN in this framework utilizes a two-stage encoder-class…
Graph Convolutional Network-based Feature Selection for High-dimensional and Low-sample Size Data
Brigham and Women’s Hospital（布莱根妇女医院）；Harvard Medical School（哈佛医学院）；Carl R. Woese Institute of Genomic Biology（卡尔·R·沃斯基因组生物学研究所）；University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
University of Bucharest（布加勒斯特大学）；“Carol Davila” University of Medicine and Pharmacy（“卡罗尔·达维拉”医药大学）；Colţea Hospital（科尔察医院）；University Politehnica of Bucharest（布加勒斯特理工大学）；MBZ University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；Linköping University（林雪平大学）
Super-resolving medical images can help physicians in providing more accurate diagnostics. In many situations, computed tomography (CT) or magnetic resonance imaging (MRI) techniques capture several scans (modes) during a single investigation, which can jointly be used (in a multimodal fashion) to further boost the quality of super-resolution results. To this end, we propose a novel multimodal multi-head convolutional attention module to super-resolve CT and MRI scans. Our attention module uses the convolution operation to perform joint spatial-channel attention on multiple concatenated input …
University of New Brunswick（新不伦瑞克大学）；University of Toronto（多伦多大学）
Neural Architecture Search (NAS) has shifted network design from using human intuition to leveraging search algorithms guided by evaluation metrics. We study channel size optimization in convolutional neural networks (CNN) and identify the role it plays in model accuracy and complexity. Current channel size selection methods are generally limited by discrete sample spaces while suffering from manual iteration and simple heuristics. To solve this, we introduce an efficient dynamic scaling algorithm -- CONet -- that automatically optimizes channel sizes across network layers for a given CNN. Two…
New York University（纽约大学）；Carnegie Mellon University（卡内基梅隆大学）；Flatiron Institute（弗莱德哈钦森研究所）；Princeton University（普林斯顿大学）
Cosmological surveys aim at answering fundamental questions about our Universe, including the nature of dark matter or the reason of unexpected accelerated expansion of the Universe. In order to answer these questions, two important ingredients are needed: 1) data from observations and 2) a theoretical model that allows fast comparison between observation and theory. Most of the cosmological surveys observe galaxies, which are very difficult to model theoretically due to the complicated physics involved in their formation and evolution; modeling realistic galaxies over cosmological volumes req…
Modern deep convolutional networks (CNNs) are often criticized for not generalizing under distributional shifts. However, several recent breakthroughs in transfer learning suggest that these networks can cope with severe distribution shifts and successfully adapt to new tasks from a few training examples. In this work we study the interplay between out-of-distribution and transfer performance of modern image classification CNNs for the first time and investigate the impact of the pre-training data size, the model scale, and the data preprocessing pipeline. We find that increasing both the trai…
Depthwise convolution is becoming increasingly popular in modern efficient ConvNets, but its kernel size is often overlooked. In this paper, we systematically study the impact of different kernel sizes, and observe that combining the benefits of multiple kernel sizes can lead to better accuracy and efficiency. Based on this observation, we propose a new mixed depthwise convolution (MixConv), which naturally mixes up multiple kernel sizes in a single convolution. As a simple drop-in replacement of vanilla depthwise convolution, our MixConv improves the accuracy and efficiency for existing Mobil…
Institute of Physics（物理研究所）；École Polytechnique Fédérale de Lausanne（洛桑联邦理工学院）
Convolutional neural networks perform a local and translationally-invariant treatment of the data: quantifying which of these two aspects is central to their success remains a challenge. We study this problem within a teacher-student framework for kernel regression, using `convolutional' kernels inspired by the neural tangent kernel of simple convolutional architectures of given filter size. Using heuristic methods from physics, we find in the ridgeless case that locality is key in determining the learning curve exponent $β$ (that relates the test error $ε_t\sim P^{-β}$ to the size of the trai…
SFCNeXt: a simple fully convolutional network for effective brain age estimation with small sample size
Zhejiang University（浙江大学）；Binjiang Institute of Zhejiang University（浙江大学滨江研究院）；Arizona State University（亚利桑那州立大学）；The First Hospital of Lanzhou University（兰州大学第一医院）
Leading University（领先大学）；Clemson University（克莱姆森大学）
We apply convolutional neural networks to identify between malaria infected and non-infected segmented cells from the thin blood smear slide images. We optimize our model to find over 95% accuracy in malaria cell detection. We also apply Canny image processing to reduce training file size while maintaining comparable accuracy (~ 94%).
The conventional spatial convolution layers in the Convolutional Neural Networks (CNNs) are computationally expensive at the point where the training time could take days unless the number of layers, the number of training images or the size of the training images are reduced. The image size of 256x256 pixels is commonly used for most of the applications of CNN, but this image size is too small for applications like Diabetic Retinopathy (DR) classification where the image details are important for accurate classification. This research proposed Frequency Domain Convolution (FDC) and Frequency …
Central University of Finance and Economics（中央财经大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of York（约克大学）
In this paper, we develop a new aligned vertex convolutional network model to learn multi-scale local-level vertex features for graph classification. Our idea is to transform the graphs of arbitrary sizes into fixed-sized aligned vertex grid structures, and define a new vertex convolution operation by adopting a set of fixed-sized one-dimensional convolution filters on the grid structure. We show that the proposed model not only integrates the precise structural correspondence information between graphs but also minimises the loss of structural information residing on local-level vertices. Exp…
Deep convolutional neural networks take GPU days of compute time to train on large data sets. Pedestrian detection for self driving cars requires very low latency. Image recognition for mobile phones is constrained by limited processing resources. The success of convolutional neural networks in these situations is limited by how fast we can compute them. Conventional FFT based convolution is fast for large filters, but state of the art convolutional neural networks use small, 3x3 filters. We introduce a new class of fast algorithms for convolutional neural networks using Winograd's minimal fil…
We introduce a fully convolutional fractional scaling component, FCFS. Fully convolutional networks can be applied to any size input and previously did not support non-integer scaling. Our architecture is simple with an efficient single layer implementation. Examples and code implementations of three common scaling methods are published.
Tsinghua University（清华大学）；Georgia Institute of Technology（佐治亚理工学院）；Ant Financial（蚂蚁金服集团(Ant Financial)）；TNList Lab（TNList实验室）；State Key Lab for Intell. Tech. & Sys.（智能技术与系统国家重点实验室）；Dept. of Comp. Sci. & Tech.（计算机科学与技术系）
Graph convolutional networks (GCNs) are powerful deep neural networks for graph-structured data. However, GCN computes the representation of a node recursively from its neighbors, making the receptive field size grow exponentially with the number of layers. Previous attempts on reducing the receptive field size by subsampling neighbors do not have a convergence guarantee, and their receptive field size per node is still in the order of hundreds. In this paper, we develop control variate based algorithms which allow sampling an arbitrarily small neighbor size. Furthermore, we prove new theoreti…
Explicit encoding of group actions in deep features makes it possible for convolutional neural networks (CNNs) to handle global deformations of images, which is critical to success in many vision tasks. This paper proposes to decompose the convolutional filters over joint steerable bases across the space and the group geometry simultaneously, namely a rotation-equivariant CNN with decomposed convolutional filters (RotDCF). This decomposition facilitates computing the joint convolution, which is proved to be necessary for the group equivariance. It significantly reduces the model size and compu…
School of Computing, Tokyo Institute of Technology（东京工业大学计算学院）；NVIDIA（英伟达）；Global Scientific Information and Computing Center, Tokyo Institute of Technology（东京工业大学全球科学信息与计算中心）；RIKEN Center for Computational Science（理化学研究所计算科学中心）
Large-scale distributed training of deep neural networks suffer from the generalization gap caused by the increase in the effective mini-batch size. Previous approaches try to solve this problem by varying the learning rate and batch size over epochs and layers, or some ad hoc modification of the batch normalization. We propose an alternative approach using a second-order optimization method that shows similar generalization capability to first-order methods, but converges faster and can handle larger mini-batches. To test our method on a benchmark where highly optimized first-order methods ar…
Shanghai University（上海大学）；University of Hawai‘i at Mānoa（夏威夷大学马诺阿分校）
Bearing fault identification and analysis is an important research area in the field of machinery fault diagnosis. Aiming at the common faults of rolling bearings, we propose a data-driven diagnostic algorithm based on the characteristics of bearing vibrations called multi-size kernel based adaptive convolutional neural network (MSKACNN). Using raw bearing vibration signals as the inputs, MSKACNN provides vibration feature learning and signal classification capabilities to identify and analyze bearing faults. Ball mixing is a ball bearing production quality problem that is difficult to identif…
Arizona State University（亚利桑那州立大学）；Nanyang Technological University（南洋理工大学）
FPGA-based hardware accelerators for convolutional neural networks (CNNs) have obtained great attentions due to their higher energy efficiency than GPUs. However, it is challenging for FPGA-based solutions to achieve a higher throughput than GPU counterparts. In this paper, we demonstrate that FPGA acceleration can be a superior solution in terms of both throughput and energy efficiency when a CNN is trained with binary constraints on weights and activations. Specifically, we propose an optimized FPGA accelerator architecture tailored for bitwise convolution and normalization that features mas…
Extremely efficient convolutional neural network architectures are one of the most important requirements for limited-resource devices (such as embedded and mobile devices). The computing power and memory size are two important constraints of these devices. Recently, some architectures have been proposed to overcome these limitations by considering specific hardware-software equipment. In this paper, the lightweight residual densely connected blocks are proposed to guaranty the deep supervision, efficient gradient flow, and feature reuse abilities of convolutional neural network. The proposed …
UCLA（加州大学洛杉矶分校）；Los Alamos National Laboratory（洛斯阿拉莫斯国家实验室）
While a number of different algorithms have recently been proposed for convolutional dictionary learning, this remains an expensive problem. The single biggest impediment to learning from large training sets is the memory requirements, which grow at least linearly with the size of the training set since all existing methods are batch algorithms. The work reported here addresses this limitation by extending online dictionary learning ideas to the convolutional context.
Washington University in St. Louis（圣路易斯华盛顿大学）；NVIDIA（英伟达）
Convolutional neural networks (CNN) are increasingly used in many areas of computer vision. They are particularly attractive because of their ability to "absorb" great quantities of labeled data through millions of parameters. However, as model sizes increase, so do the storage and memory requirements of the classifiers. We present a novel network architecture, Frequency-Sensitive Hashed Nets (FreshNets), which exploits inherent redundancy in both convolutional layers and fully-connected layers of a deep learning model, leading to dramatic savings in memory and storage consumption. Based on th…
Image classification is considered, and a hierarchical max-pooling model with additional local pooling is introduced. Here the additional local pooling enables the hierachical model to combine parts of the image which have a variable relative distance towards each other. Various convolutional neural network image classifiers are introduced and compared in view of their rate of convergence. The finite sample size performance of the estimates is analyzed by applying them to simulated and real data.
Although Convolutional Neural Networks (CNNs) are widely used, their translation invariance (ability to deal with translated inputs) is still subject to some controversy. We explore this question using translation-sensitivity maps to quantify how sensitive a standard CNN is to a translated input. We propose the use of Cosine Similarity as sensitivity metric over Euclidean Distance, and discuss the importance of restricting the dimensionality of either of these metrics when comparing architectures. Our main focus is to investigate the effect of different architectural components of a standard C…
This paper presents an iterative pruning strategy for Convolutional Network Fabrics (CNF) in presence of noisy training and testing data. With the continuous increase in size of neural network models, various authors have developed pruning approaches to build more compact network structures requiring less resources, while preserving performance. As we show in this paper, because of their intrinsic structure and function, Convolutional Network Fabrics are ideal candidates for pruning. We present a series of pruning strategies that can significantly reduce both the final network size and require…
Deep learning models are now used in many different industries, while in certain domains safety is not a critical issue in the medical field it is a huge concern. Not only, we want the models to generalize well but we also want to know the models confidence respect to its decision and which features matter the most. Our team aims to develop a full pipeline in which not only displays the uncertainty of the models decision but also, the saliency map to show which sets of pixels of the input image contribute most to the predictions.
Convolutional rectifier networks, i.e. convolutional neural networks with rectified linear activation and max or average pooling, are the cornerstone of modern deep learning. However, despite their wide use and success, our theoretical understanding of the expressive properties that drive these networks is partial at best. On the other hand, we have a much firmer grasp of these issues in the world of arithmetic circuits. Specifically, it is known that convolutional arithmetic circuits possess the property of "complete depth efficiency", meaning that besides a negligible set, all functions that…
Recently, nested dropout was proposed as a method for ordering representation units in autoencoders by their information content, without diminishing reconstruction cost. However, it has only been applied to training fully-connected autoencoders in an unsupervised setting. We explore the impact of nested dropout on the convolutional layers in a CNN trained by backpropagation, investigating whether nested dropout can provide a simple and systematic way to determine the optimal representation size with respect to the desired accuracy and desired task and data complexity.
Unordered feature sets are a nonstandard data structure that traditional neural networks are incapable of addressing in a principled manner. Providing a concatenation of features in an arbitrary order may lead to the learning of spurious patterns or biases that do not actually exist. Another complication is introduced if the number of features varies between each set. We propose convolutional deep averaging networks (CDANs) for classifying and learning representations of datasets whose instances comprise variable-size, unordered feature sets. CDANs are efficient, permutation-invariant, and cap…
Politecnico di Torino（都灵理工大学）；University of Bologna（博洛尼亚大学）
Temporal Convolutional Networks (TCNs) are promising Deep Learning models for time-series processing tasks. One key feature of TCNs is time-dilated convolution, whose optimization requires extensive experimentation. We propose an automatic dilation optimizer, which tackles the problem as a weight pruning on the time-axis, and learns dilation factors together with weights, in a single training. Our method reduces the model size and inference latency on a real SoC hardware target by up to 7.4x and 3x, respectively with no accuracy drop compared to a network without dilation. It also yields a ric…
Hebrew University（希伯来大学）；School of Computer Science（计算机科学学院）
Convolutional neural networks (CNN) exhibit unmatched performance in a multitude of computer vision tasks. However, the advantage of using convolutional networks over fully-connected networks is not understood from a theoretical perspective. In this work, we show how convolutional networks can leverage locality in the data, and thus achieve a computational advantage over fully-connected networks. Specifically, we show a class of problems that can be efficiently solved using convolutional networks trained with gradient-descent, but at the same time is hard to learn using a polynomial-size fully…
Most of the research in convolutional neural networks has focused on increasing network depth to improve accuracy, resulting in a massive number of parameters which restricts the trained network to platforms with memory and processing constraints. We propose to modify the structure of the Very Deep Convolutional Neural Networks (VDCNN) model to fit mobile platforms constraints and keep performance. In this paper, we evaluate the impact of Temporal Depthwise Separable Convolutions and Global Average Pooling in the network parameters, storage size, and latency. The squeezed model (SVDCNN) is bet…
To protect tropical forest biodiversity, we need to be able to detect it reliably, cheaply, and at scale. Automated species detection from passively recorded soundscapes via machine-learning approaches is a promising technique towards this goal, but it is constrained by the necessity of large training data sets. Using soundscapes from a tropical forest in Borneo and a Convolutional Neural Network model (CNN) created with transfer learning, we investigate i) the minimum viable training data set size for accurate prediction of call types ('sonotypes'), and ii) the extent to which data augmentati…
Central University of Finance and Economics（中央财经大学）；Southern University of Science and Technology（南方科技大学）；University of York（约克大学）
In this paper, we develop a novel Backtrackless Aligned-Spatial Graph Convolutional Network (BASGCN) model to learn effective features for graph classification. Our idea is to transform arbitrary-sized graphs into fixed-sized backtrackless aligned grid structures and define a new spatial graph convolution operation associated with the grid structures. We show that the proposed BASGCN model not only reduces the problems of information loss and imprecise information representation arising in existing spatially-based Graph Convolutional Network (GCN) models, but also bridges the theoretical gap b…
Cornell University（康奈尔大学）；Harvard University（哈佛大学）；Technical University of Munich（慕尼黑工业大学）；Institute for Advanced Study（高等研究院）；Munich Center for Quantum Science and Technology（慕尼黑量子科学与技术中心）；Princeton University（普林斯顿大学）
Machine learning models are a powerful theoretical tool for analyzing data from quantum simulators, in which results of experiments are sets of snapshots of many-body states. Recently, they have been successfully applied to distinguish between snapshots that can not be identified using traditional one and two point correlation functions. Thus far, the complexity of these models has inhibited new physical insights from this approach. Here, using a novel set of nonlinearities we develop a network architecture that discovers features in the data which are directly interpretable in terms of physic…
In this work I propose a new way of using fully convolutional networks for classification while allowing for input of any size. I additionally propose two modifications on the idea of attention and the benefits and detriments of using the modifications. Finally, I show suboptimal results on the ITAmoji 2018 tweet to emoji task and provide a discussion about why that might be the case as well as a proposed fix to further improve results.
In this paper, we introduce Channel-wise recurrent convolutional neural networks (RecNets), a family of novel, compact neural network architectures for computer vision tasks inspired by recurrent neural networks (RNNs). RecNets build upon Channel-wise recurrent convolutional (CRC) layers, a novel type of convolutional layer that splits the input channels into disjoint segments and processes them in a recurrent fashion. In this way, we simulate wide, yet compact models, since the number of parameters is vastly reduced via the parameter sharing of the RNN formulation. Experimental results on the…
Graph processes model a number of important problems such as identifying the epicenter of an earthquake or predicting weather. In this paper, we propose a Graph Convolutional Recurrent Neural Network (GCRNN) architecture specifically tailored to deal with these problems. GCRNNs use convolutional filter banks to keep the number of trainable parameters independent of the size of the graph and of the time sequences considered. We also put forward Gated GCRNNs, a time-gated variation of GCRNNs akin to LSTMs. When compared with GNNs and another graph recurrent architecture in experiments using both…
We introduce a convolutional neural network that operates directly on graphs. These networks allow end-to-end learning of prediction pipelines whose inputs are graphs of arbitrary size and shape. The architecture we present generalizes standard molecular feature extraction methods based on circular fingerprints. We show that these data-driven features are more interpretable, and have better predictive performance on a variety of tasks.
