Objectives NaV1.7 is a key target related to pain. This study focused on predicting and optimizing inhibitors of NaV1.7 using machine learning methods, and using patch-clamp methods to validate them at the cellular level. Materials and Methods We used Chembl, BindingDB, and data from the literature to establish classification models for inhibitors. The imbalanced data set test2 was used to screen the best-performing model to screen commercial compound libraries, and whole-cell voltage-clamp was used to validate inhibitors. We propose a molecular group optimization method using a combination of Grammer Variational Autoencoder, classification model, and simulated annealing algorithm. Results and Conclusion We get the model RF-CDK that performs best in the imbalanced data set. Of the three compounds that may have inhibitory effects, Nortriptyline has been experimentally verified. In the molecular optimization method, the best result of the optimization results of CHEMBL2325245 is MS = 1.052, PROB = 0.527, SA = 2.587, QED = 0.462. 40 molecules located in the applicability domain of RF-CDK were used for optimization, among which 34 molecules gave larger MS values.

Sequential and temporal data arise in many fields of research, such as quantitative finance, medicine, or computer vision. The present article is concerned with a novel approach for sequential learning, called the signature method, and rooted in rough path theory. Its basic principle is to represent multidimensional paths by a graded feature set of their iterated integrals, called the signature. This approach relies critically on an embedding principle, which consists in representing discretely sampled data as paths, i.e., functions from $[0,1]$ to $R^d$. After a survey of machine learning methodologies for signatures, we investigate the influence of embeddings on prediction accuracy with an in-depth study of three recent and challenging datasets. We show that a specific embedding, called lead-lag, is systematically better, whatever the dataset or algorithm used. Moreover, we emphasize through an empirical study that computing signatures over the whole path domain does not lead to a loss of local information. We conclude that, with a good embedding, the signature combined with a simple algorithm achieves results competitive with state-of-the-art, domain-specific approaches.

Because tensor data appear more and more frequently in various scientific researches and real-world applications, analyzing the relationship between tensor features and the univariate outcome becomes an elementary task in many fields. To solve this task, we propose \underline{Fa}st \underline{S}parse \underline{T}ensor \underline{R}egression model (FasTR) based on so-called unit-rank CANDECOMP/PARAFAC decomposition. FasTR first decomposes the tensor coefficient into component vectors and then estimates each vector with $\ell_1$ regularized regression. Because of the independence of component vectors, FasTR is able to solve in a parallel way and the time complexity is proved to be superior to previous models. We evaluate the performance of FasTR on several simulated datasets and a real-world fMRI dataset. Experiment results show that, compared with four baseline models, in every case, FasTR can compute a better solution within less time.

Such behavior is desirable in multivariate structured prediction tasks, where handcrafted per-pixel loss-based methods inadequately capture strong correlations between output dimensions. CNFs are efficient in sampling and inference, they can be trained with a likelihood-based objective, and CNFs, being generative flows, do not suffer from mode collapse or training instabilities. We provide an effective method to train continuous CNFs for binary problems and in particular, we apply these CNFs to super-resolution and vessel segmentation tasks demonstrating competitive performance on standard benchmark datasets in terms of likelihood and conventional metrics. When the output y is high-dimensional this is a particularly challenging task, and the practitioner is left with many design choices. Do we factorize the conditional? If not, do we model correlations with, say, a conditional random field (Prince, 2012)? Do we use a unimodal distribution? How fat should the tails be? Do we use an explicit likelihood at all, or use implicit methods (Mohamed & Rezende, 2015) such as a GAN (Goodfellow et al., 2014)? Do we quantize the output?

The gradient noise (GN) in the stochastic gradient descent (SGD) algorithm is often considered to be Gaussian in the large data regime by assuming that the \emph{classical} central limit theorem (CLT) kicks in. This assumption is often made for mathematical convenience, since it enables SGD to be analyzed as a stochastic differential equation (SDE) driven by a Brownian motion. We argue that the Gaussianity assumption might fail to hold in deep learning settings and hence render the Brownian motion-based analyses inappropriate. Inspired by non-Gaussian natural phenomena, we consider the GN in a more general context and invoke the \emph{generalized} CLT, which suggests that the GN converges to a \emph{heavy-tailed} $\alpha$-stable random vector, where \emph{tail-index} $\alpha$ determines the heavy-tailedness of the distribution. Accordingly, we propose to analyze SGD as a discretization of an SDE driven by a L\'{e}vy motion. Such SDEs can incur `jumps', which force the SDE and its discretization \emph{transition} from narrow minima to wider minima, as proven by existing metastability theory and the extensions that we proved recently. In this study, under the $\alpha$-stable GN assumption, we further establish an explicit connection between the convergence rate of SGD to a local minimum and the tail-index $\alpha$. To validate the $\alpha$-stable assumption, we conduct experiments on common deep learning scenarios and show that in all settings, the GN is highly non-Gaussian and admits heavy-tails. We investigate the tail behavior in varying network architectures and sizes, loss functions, and datasets. Our results open up a different perspective and shed more light on the belief that SGD prefers wide minima.

"Thinking in pictures," [1] i.e., spatial-temporal reasoning, effortless and instantaneous for humans, is believed to be a significant ability to perform logical induction and a crucial factor in the intellectual history of technology development. Modern Artificial Intelligence (AI), fueled by massive datasets, deeper models, and mighty computation, has come to a stage where (super-)human-level performances are observed in certain specific tasks. However, current AI's ability in "thinking in pictures" is still far lacking behind. In this work, we study how to improve machines' reasoning ability on one challenging task of this kind: Raven's Progressive Matrices (RPM). Specifically, we borrow the very idea of "contrast effects" from the field of psychology, cognition, and education to design and train a permutation-invariant model. Inspired by cognitive studies, we equip our model with a simple inference module that is jointly trained with the perception backbone. Combining all the elements, we propose the Contrastive Perceptual Inference network (CoPINet) and empirically demonstrate that CoPINet sets the new state-of-the-art for permutation-invariant models on two major datasets. We conclude that spatial-temporal reasoning depends on envisaging the possibilities consistent with the relations between objects and can be solved from pixel-level inputs.

In this paper, we describe NeurIPS 2019 Learning to Move - Walk Around challenge physics-based environment and present our solution to this competition which scored 1303.727 mean reward points and took 3rd place. Our method combines recent advances from both continuous- and discrete-action space reinforcement learning, such as Soft Actor-Critic and Recurrent Experience Replay in Distributed Reinforcement Learning. We trained our agent in two stages: to move somewhere at the first stage and to follow the target velocity field at the second stage. We also introduce novel Q-function split technique, which we believe facilitates the task of training an agent, allows critic pretraining and reusing it for solving harder problems, and mitigate reward shaping design efforts.

Adversarial or test time robustness measures the susceptibility of a machine learning system to small perturbations made to the input at test time. This has attracted much interest on the empirical side, since many existing ML systems perform poorly under imperceptible adversarial perturbations to the test inputs. On the other hand, our theoretical understanding of this phenomenon is limited, and has mostly focused on supervised learning tasks. In this work we study the problem of computing adversarially robust representations of data. We formulate a natural extension of Principal Component Analysis (PCA) where the goal is to find a low dimensional subspace to represent the given data with minimum projection error, and that is in addition robust to small perturbations measured in $\ell_q$ norm (say $q=\infty$). Unlike PCA which is solvable in polynomial time, our formulation is computationally intractable to optimize as it captures the well-studied sparse PCA objective. We show the following algorithmic and statistical results. - Polynomial time algorithms in the worst-case that achieve constant factor approximations to the objective while only violating the robustness constraint by a constant factor. - We prove that our formulation (and algorithms) also enjoy significant statistical benefits in terms of sample complexity over standard PCA on account of a "regularization effect", that is formalized using the well-studied spiked covariance model. - Surprisingly, we show that our algorithmic techniques can also be made robust to corruptions in the training data, in addition to yielding representations that are robust at test time! Here an adversary is allowed to corrupt potentially every data point up to a specified amount in the $\ell_q$ norm. We further apply these techniques for mean estimation and clustering under adversarial corruptions to the training data.

Public road authorities and private mobility service providers need information derived from the current and predicted traffic states to act upon the daily urban system and its spatial and temporal dynamics. In this research, a real-time parking area state (occupancy, in- and outflux) prediction model (up to 60 minutes ahead) has been developed using publicly available historic and real time data sources. Based on a case study in a real-life scenario in the city of Arnhem, a Neural Network-based approach outperforms a Random Forest-based one on all assessed performance measures, although the differences are small. Both are outperforming a naive seasonal random walk model. Although the performance degrades with increasing prediction horizon, the model shows a performance gain of over 150% at a prediction horizon of 60 minutes compared with the naive model. Furthermore, it is shown that predicting the in- and outflux is a far more difficult task (i.e. performance gains of 30%) which needs more training data, not based exclusively on occupancy rate. However, the performance of predicting in- and outflux is less sensitive to the prediction horizon. In addition, it is shown that real-time information of current occupancy rate is the independent variable with the highest contribution to the performance, although time, traffic flow and weather variables also deliver a significant contribution. During real-time deployment, the model performs three times better than the naive model on average. As a result, it can provide valuable information for proactive traffic management as well as mobility service providers.

In few-shot learning, typically, the loss function which is applied at test time is the one we are ultimately interested in minimising, such as the mean-squared-error loss for a regression problem. However, given that we have few samples at test time, we argue that the loss function that we are interested in minimising is not necessarily the loss function most suitable for computing gradients in a few-shot setting. We propose VIABLE, a generic meta-learning extension that builds on existing meta-gradient-based methods by learning a differentiable loss function, replacing the pre-defined inner-loop loss function in performing task-specific updates. We show that learning a loss function capable of leveraging relational information between samples reduces underfitting, and significantly improves performance and sample efficiency on a simple regression task. Furthermore, we show VIABLE is scalable by evaluating on the Mini-Imagenet dataset.