Nonlinear Clustering Research Articles

Enhancing Streamflow Prediction in Ungauged Basins Using a Nonlinear Knowledge‐Based Framework and Deep Learning

AbstractIn hydrology, a fundamental task involves enhancing the predictive power of a model in ungagged basins by transferring information on physical attributes and hydroclimate dynamics from gauged basins. Introducing an integrated nonlinear clustering framework, this study aims to develop a comprehensive framework that augments predictive performance in basins where direct measurements are sparse or absent. In this framework, uniform manifold approximation and projection (UMAP) is used as a nonlinear method to extract the essential features embedded in hydro‐climatological attributes and physical properties. Then, the Growing Neural Gas (GNG) clustering model is used to find the basins that potentially share similar hydro‐climatological behaviors. Besides UMAP‐GNG, the integration of Principal Component Analysis (PCA) as a linear method to reduce dimensionality with common clustering methods are also assessed to serve as benchmarks. The results reveal that the combination of clustering algorithms with the PCA method may lead to loss of information while the nonlinear method (UMAP) can extract more informative features. The efficacy of the proposed framework is assessed across the Contiguous United States (CONUS) by training a single Base Model using long short‐term memory (LSTM) for the centroids of all clusters and then, fine‐tuning the model on the centroids of each cluster separately to create a regional model. The results indicate that using the information extracted by the UMAP‐GNG method to guide a Base Model can significantly improve the accuracy in most of the clusters and enhance the median prediction accuracy within different clusters from 0.04 to 0.37 of KGE in ungauged basins.

Characterizing urban acoustic environments by clustering sensor node measurements

Equivalent sound pressure levels have been widely used to assess the impact of the sonic environment on persons. At the same time, it has been demonstrated that sound sensor networks allow to extract a wealth of information about the living environment. Nevertheless it has not been clearly demonstrated how to summarize this information. To this end, we used advanced non-linear clustering methods to group 15-minute sound environments based on a wide range of classical acoustic indicators such as peak levels, statistical levels, spectral center of gravity. Machine learning methods identifying the sound sources that are present based on 1/3 octave band levels measured at 125 msec interval, are then used to better understand why these clusters emerge. The methodology is applied to 150 bedroom window measurements gathered in the Equal-Life project. Preliminary results show that groups of pre-school children with specific cognitive development and mental health are related to different diurnal patterns of sound environment clusters. These results can be interpreted in the larger context of living environments extracted from environmental sound sensing networks.

GAP: A group-based automatic pruning algorithm via convolution kernel fusion

In recent years, the deployment and operation of convolution neural networks on edge devices with limited computing capabilities have become increasingly challenging due to the large network structure and computational cost. Currently, the mainstream structured pruning algorithms mainly compress the network at the filter or layer level. However, these methods introduce too much human intervention with large granularities, which may lead to unpredictable performance after compression. In this paper, we propose a group-based automatic pruning algorithm(GAP) via kernel fusion to automatically search for the optimal pruning structure in a more fine-grained manner. Specifically, we first adopt a novel nonlinear dimensionality reduction clustering algorithm to divide the filters of each convolution layer into groups of equal size. Afterwards, we encode the mutual distribution similarity of the kernels within each group, and its KL divergence is employed as an importance indicator to determine the retained kernel groups through weighted fusion. Subsequently, we introduce an intelligent searching module that automatically explore and optimize the pruned structure of each layer. Finally, the pruned filters are permutated to form a dense group convolution and fine-tuned. Sufficient experiments show that, on two image classification datasets, for five advanced CNN models, our GAP algorithm outperforms most extant SOTA schemes, reduces artificial intervention, and enables efficient end-to-end training of compact models.

A multi-symptomatic model of heroin use disorder in rats reveals distinct behavioral profiles and neuronal correlates of heroin vulnerability versus resiliency.

The behavioral and diagnostic heterogeneity within human opioid use disorder (OUD) diagnosis is not readily captured in current animal models, limiting translational relevance of the mechanistic research that is conducted in experimental animals. We hypothesize that a non-linear clustering of OUD-like behavioral traits will capture population heterogeneity and yield subpopulations of OUD vulnerable rats with distinct behavioral and neurocircuit profiles. Over 900 male and female heterogeneous stock rats, a line capturing genetic and behavioral heterogeneity present in humans, were assessed for several measures of heroin use and rewarded and non-rewarded seeking behaviors. Using a non-linear stochastic block model clustering analysis, rats were assigned to OUD vulnerable, intermediate and resilient clusters. Additional behavioral tests and circuit analyses using c-fos protein activation were conducted on the vulnerable and resilient subpopulations. OUD vulnerable rats exhibited greater heroin taking and seeking behaviors relative to those in the intermediate and resilient clusters. Akin to human OUD diagnosis, further vulnerable rat sub-clustering revealed subpopulations with different combinations of behavioral traits, including sex differences. Lastly, heroin cue-induced neuronal patterns of circuit activation differed between resilient and vulnerable phenotypes. Behavioral sex differences were recapitulated in patterns of circuitry activation, including males preferentially engaging extended amygdala stress circuitry, and females cortico-striatal drug cue-seeking circuitry. Using a non-linear clustering approach in rats, we captured behavioral diagnostic heterogeneity reflective of human OUD diagnosis. OUD vulnerability and resiliency were associated with distinct neuronal activation patterns, posing this approach as a translational tool in assessing neurobiological mechanisms underpinning OUD.

One-Stage Shifted Laplacian Refining for Multiple Kernel Clustering.

Graph learning can effectively characterize the similarity structure of sample pairs, hence multiple kernel clustering based on graph learning (MKC-GL) achieves promising results on nonlinear clustering tasks. However, previous methods confine to a "three-stage" scheme, that is, affinity graph learning, Laplacian construction, and clustering indicator extracting, which results in the information distortion in the step alternating. Meanwhile, the energy of Laplacian reconstruction and the necessary cluster information cannot be preserved simultaneously. To address these problems, we propose a one-stage shifted Laplacian refining (OSLR) method for multiple kernel clustering (MKC), where using the "one-stage" scheme focuses on Laplacian learning rather than traditional graph learning. Concretely, our method treats each kernel matrix as an affinity graph rather than ordinary data and constructs its corresponding Laplacian matrix in advance. Compared to the traditional Laplacian methods, we transform each Laplacian to an approximately shifted Laplacian (ASL) for refining a consensus Laplacian. Then, we project the consensus Laplacian onto a Fantope space to ensure that reconstruction information and clustering information concentrate on larger eigenvalues. Theoretically, our OSLR reduces the memory complexity and computation complexity to O(n) and O(n2) , respectively. Moreover, experimental results have shown that it outperforms state-of-the-art MKC methods on multiple benchmark datasets.

Hypergraph-based convex semi-supervised unconstraint symmetric matrix factorization for image clustering

Semi-supervised symmetric nonnegative matrix factorization (SNMF) has been extensively utilized in both linear and nonlinear data clustering tasks. However, the current SNMF model's non-convex objective function faces challenges in global optimization and time efficiency. In this study, we leverage label information to propose a convex and unconstrained symmetric matrix factorization (SMF) model that is thoroughly analyzed for its convexity properties. In order to capture high-order relationships among data, a hypergraph is utilized in the model, which is computationally simple, translation invariant, and naturally normalized. Moreover, based on the analysis and the corresponding experiments in the paper, the model exhibits robustness towards outliers to some extent. Due to the convexity of our proposed model without constraint, it can be efficiently optimized using the Conjugate Gradient (CG) method, one of the most efficient methods available. Therefore, we propose a novel Convex Combination-based Sufficient Descent CG (CSDCG) method, which outperforms other methods across 284 optimization problems within the CUTEst library. In order to evaluate the effectiveness of the proposed method, the semi-supervised clustering experiments are conducted on the eight datasets by comparison with ten state-of-the-art matrix factorization (MF) methods. The experiment results demonstrate its superiority over the other compared methods to handle the clustering problem with better performance and less computational time. The code is available at https://github.com/Pokemer/HCSSMF.

Methods and algorithms of swarm intelligence for the problems of nonlinear regression analysis and optimization of complex processes, objects, and systems: review and modification of methods and algorithms

The development of high-speed methods and algorithms for global multidimensional optimization and their modifications in various fields of science, technology, and economics is an urgent problem that involves reducing computing costs, accelerating, and effectively searching for solutions to such problems. Since most serious problems involve the search for tens, hundreds, or thousands of optimal parameters of mathematical models, the search space for these parameters grows non-linearly. Currently, there are many modern methods and algorithms of swarm intelligence that solve today's scientific and applied problems, but they require modifications due to the large spaces of searching for optimal model parameters. Modern swarm intelligence has significant potential for application in the energy industry due to its ability to optimize and solve complex problems. It can be used to solve scientific and applied problems of optimizing energy consumption in buildings, industrial complexes, and urban systems, reducing energy losses, and increasing the efficiency of resource use, as well as for the construction of various elements of energy systems in general. Well-known methods and algorithms of swarm intelligence are also actively applied to forecast energy production from renewable sources, such as solar and wind energy. This allows better management of energy sources and planning of their use. The relevance of modifications of methods and algorithms is due to the issues of speeding up their work when solving machine learning problems, in particular, in nonlinear regression models, classification, and clustering problems, where the number of observed data can reach tens and hundreds of thousands or more. The work considers and modifies well-known effective methods and algorithms of swarm intelligence (particle swarm optimization algorithm, bee optimization algorithm, differential evolution method) for finding solutions to multidimensional extremal problems with and without restrictions, as well as problems of nonlinear regression analysis. The obtained modifications of the well-known classic effective methods and algorithms of swarm intelligence, which are present in the work, effectively solve complex scientific and applied tasks of designing complex objects and systems. A comparative analysis of methods and algorithms will be conducted in the next study on this topic. Keywords: optimization, swarm intelligence, mathematical modelling, nonlinear regression, complex objects and systems.

Exploring The Impact of Stemming on Text Topic-Based Classification Accuracy

Text classification attempts to assign written texts to specific group types that share the same linguistic features. One class of features that have been widely employed for a wide range of classification tasks is lexical features. This study explores the impact of stemming on text classification using lexical features. To explore, this study is based on a corpus of thirty texts written by six authors with topics that focus on politics, history, science, prose, sport, and food. These texts are stemmed using a light stemming algorithm. In order to classify these texts according to the topic by means of lexical features, linear hierarchical clustering and non-linear clustering (SOM) is carried out on the stemmed and unstemmed texts. Although both clustering methods are able to classify texts by topic with two models produce accurate and stable results, the results suggest that the impact of a light stemming on the accuracy of text classification by topic is ineffectual. The accuracy is neither increased nor decreased on the stemmed texts, whereby the stemming algorithm helped reducing the dimensionality of feature vector space model.

Genome-wide association study reveals multiple loci for nociception and opioid consumption behaviors associated with heroin vulnerability in outbred rats.

The increased prevalence of opioid use disorder (OUD) makes it imperative to disentangle the biological mechanisms contributing to individual differences in OUD vulnerability. OUD shows strong heritability, however genetic variants contributing toward vulnerability remain poorly defined. We performed a genome-wide association study using over 850 male and female heterogeneous stock (HS) rats to identify genes underlying behaviors associated with OUD such as nociception, as well as heroin-taking, extinction and seeking behaviors. By using an animal model of OUD, we were able to identify genetic variants associated with distinct OUD behaviors while maintaining a uniform environment, an experimental design not easily achieved in humans. Furthermore, we used a novel non-linear network-based clustering approach to characterize rats based on OUD vulnerability to assess genetic variants associated with OUD susceptibility. Our findings confirm the heritability of several OUD-like behaviors, including OUD susceptibility. Additionally, several genetic variants associated with nociceptive threshold prior to heroin experience, heroin consumption, escalation of intake, and motivation to obtain heroin were identified. Tom1 , a microglial component, was implicated for nociception. Several genes involved in dopaminergic signaling, neuroplasticity and substance use disorders, including Brwd1 , Pcp4, Phb1l2 and Mmp15 were implicated for the heroin traits. Additionally, an OUD vulnerable phenotype was associated with genetic variants for consumption and break point, suggesting a specific genetic contribution for OUD-like traits contributing to vulnerability. Together, these findings identify novel genetic markers related to the susceptibility to OUD-relevant behaviors in HS rats.

Sparse kernel k-means clustering

Clustering is an essential technique that groups similar data points to uncover the underlying structure and features of the data. Although traditional clustering methods such as k-means are widely utilized, they have limitations in identifying nonlinear clusters. Thus, alternative techniques, such as kernel k-means and spectral clustering, have been developed to address this issue. However, another challenge arises when irrelevant variables are present in the data; this can be mitigated by employing variable selection methods such as the filter, wrapper, and embedded approaches. In this study, with a particular focus on kernel k-means clustering, we propose an embedded variable selection method using a tensor product space along with a general analysis of variance kernel for nonlinear clustering. Comprehensive experiments involving simulations and real data analysis demonstrated that the proposed method achieves competitive performance compared to existing approaches. Thus, the proposed method may serve as a reliable tool for accurate cluster identification and variable selection to gain insights into complex datasets.

Identifying Novel Subtypes of Functional Gastrointestinal Disorder by Analyzing Nonlinear Structure in Integrative Biopsychosocial Questionnaire Data.

Background/Objectives: Given the limited success in treating functional gastrointestinal disorders (FGIDs) through conventional methods, there is a pressing need for tailored treatments that account for the heterogeneity and biopsychosocial factors associated with FGIDs. Here, we considered the potential of novel subtypes of FGIDs based on biopsychosocial information. Methods: We collected data from 198 FGID patients utilizing an integrative approach that included the traditional Korean medicine diagnosis questionnaire for digestive symptoms (KM), as well as the 36-item Short Form Health Survey (SF-36), alongside the conventional Rome-criteria-based Korean Bowel Disease Questionnaire (K-BDQ). Multivariate analyses were conducted to assess whether KM or SF-36 provided additional information beyond the K-BDQ and its statistical relevance to symptom severity. Questions related to symptom severity were selected using an extremely randomized trees (ERT) regressor to develop an integrative questionnaire. For the identification of novel subtypes, Uniform Manifold Approximation and Projection and spectral clustering were used for nonlinear dimensionality reduction and clustering, respectively. The validity of the clusters was assessed using certain metrics, such as trustworthiness, silhouette coefficient, and accordance rate. An ERT classifier was employed to further validate the clustered result. Results: The multivariate analyses revealed that SF-36 and KM supplemented the psychosocial aspects lacking in K-BDQ. Through the application of nonlinear clustering using the integrative questionnaire data, four subtypes of FGID were identified: mild, severe, mind-symptom predominance, and body-symptom predominance. Conclusions: The identification of these subtypes offers a framework for personalized treatment strategies, thus potentially enhancing therapeutic outcomes by tailoring interventions to the unique biopsychosocial profiles of FGID patients.

Galaxy clustering multi-scale emulation

Simulation-based inference has seen increasing interest in the past few years as a promising approach to modelling the non-linear scales of galaxy clustering. The common approach, using the Gaussian process, is to train an emulator over the cosmological and galaxy–halo connection parameters independently for every scale. We present a new Gaussian process model that allows the user to extend the input parameter space dimensions and to use a non-diagonal noise covariance matrix. We use our new framework to simultaneously emulate every scale of the non-linear clustering of galaxies in redshift space from the ABACUSSUMMITN-body simulations at redshift z = 0.2. The model includes nine cosmological parameters, five halo occupation distribution (HOD) parameters, and one scale dimension. Accounting for the limited resolution of the simulations, we train our emulator on scales from 0.3 h−1 Mpc to 60 h−1 Mpc and compare its performance with the standard approach of building one independent emulator for each scale. The new model yields more accurate and precise constraints on cosmological parameters compared to the standard approach. As our new model is able to interpolate over the scale space, we are also able to account for the Alcock-Paczynski distortion effect, leading to more accurate constraints on the cosmological parameters.

Enforced Block Diagonal Graph Learning for Multikernel Clustering

The existing multikernel graph clustering (MKGC) methods have emerged with notable success on nonlinear clustering tasks since the graph learning can effectively capture graph structure similarity between sample pair. Ideally, a high-quality graph should enjoy the good block diagonal property, i.e. the intercluster similarities correspond to zeros, while intracluster similarities represent nonzeros. Meanwhile, the number of diagonal blocks for a graph equals to the number of clusters on the dataset. However, most of the existing MKGC methods design a corpulent three-parts graph leaning process that poses challenges for hyperparameter tuning, time cost, and clustering performance. To overcome these challenging issues, we propose an enforced block diagonal graph learning for multikernel clustering (EBDGL-MKC) method, where we pursue a high-quality block diagonal graph via well-designed one-part graph leaning scheme rather than three parts. Inspired by symmetric matrix factorization (SMF), we first design a one-part block diagonal graph learning scheme to learn multiple block diagonal graphs, by exploring an explicit theoretical connection between the clustering partition of kernel <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$k$</tex-math> </inline-formula> -means and the excellent block diagonal graph. Then, these block diagonal graphs are stacked into a low-rank tensor for exploiting the high-order structure information hidden in the nonlinear data. After that, an effective alternate algorithm with convergence proof is performed on extensive experiments to demonstrate the superiority of EBDGL compared with the state-of-the-art multikernel clustering (MKC) methods.

Layout optimization of irregular storage areas under class storage strategy based on clustering and multi-bin size packing problem.

This paper proposes an optimization scheme for the layout of irregular warehouse spaces based on a class-based storage strategy. Firstly, we transform the irregular warehouse space into several regular rectangular areas. Next, through the class-based storage strategy, we develop an algorithm that converts the non-linear clustering problem of homogeneous shelves into a linear selection problem of different sized regular shelf areas. Finally, a comprehensive shelving clustering algorithm and packing problem with different box sizes selection were constructed, and empirical analysis was conducted based on actual data from Xiangtai Warehouse of State Grid Corporation of China. The results show that the new model not only effectively solves the irregular warehouse layout optimization problem under the class storage strategy but also reduces the complexity of the model and shortens the solution time. It is a universally applicable method with significant value for generalization.

An emulator-based halo model in modified gravity – I. The halo concentration–mass relation and density profile

ABSTRACT In this series of papers, we present an emulator-based halo model for the non-linear clustering of galaxies in modified gravity cosmologies. In the first paper, we present emulators for the following halo properties: the halo mass function, concentration–mass relation and halo-matter cross-correlation function. The emulators are trained on data extracted from the forge and bridge suites of N-body simulations, respectively, for two modified gravity (MG) theories: f(R) gravity, and the DGP model, varying three standard cosmological parameters Ωm0, H0, σ8, and one MG parameter, either $\bar{f}_{R0}$ or rc. Our halo property emulators achieve an accuracy of ${\lesssim}1\ \hbox{per cent}$ on independent test data sets. We demonstrate that the emulators can be combined with a galaxy–halo connection prescription to accurately predict the galaxy–galaxy and galaxy–matter correlation functions using the halo model framework.

Plane-based clustering with asymmetric distribution loss

Ramp-based twin support vector clustering (RampTWSVC) is a powerful clustering method, which measures the within-cluster and between-cluster scatter by the bounded ramp functions. However, the ramp loss is a symmetric function and it does not consider the data distribution, which makes the RampTWSVC not robust enough to deal with noisy datasets. In this paper, we construct an asymmetric distribution loss function and propose a novel plane-based clustering with asymmetric distribution loss (ADPC). The asymmetric distribution loss function combined the ramp loss with first-order and second-order statistics, it inherits the advantages of ramp loss function and captures the data distribution precisely, which makes ADPC more robust to the samples far from the cluster center plane. Moreover, two adjusting parameters t1 and t2 are introduced to flexibly control the form of the asymmetric distribution loss function and improve the performance of the algorithm. In addition, its nonlinear clustering formation is also provided by using the kernel trick. Some experiments on noise-corrupted benchmark UCI and artificial datasets have been provided, and the detailed comparison results show that the proposed ADPC has better performance on most datasets. Further experiments and analysis on the face clustering have been done to demonstrate the effectiveness and feasibility of the proposed ADPC.

Deep robust multi-channel learning subspace clustering networks

Subspace clustering methods are now widely used for unsupervised high-dimensional data processing in computer vision and other domains. Deep subspace clustering methods based on auto-encoder networks have made a significant improvement in nonlinear subspace clustering problems in comparison to previous works. However, these methods ignore the valid information lost during feature extraction, resulting in incomplete information and imprecise feature representations for subspace clustering. In addition, the clustering performance of the existing clustering methods is excessively dependent on hyper-parameters, making training difficult and unstable. In this paper, we propose Deep Robust Multi-Channel Learning Subspace Clustering Networks (DRMCLSC), a novel deep subspace clustering network for learning more comprehensive feature representations with good robustness for subspace clustering. The multi-channel learning strategy allows the model to extract, retain and fuse features simultaneously, enabling all valid information from the sample data to be obtained. Moreover, the multi-channel learning structure of the proposed method produces a more stable integration network that is less dependent on hyper-parameters and more resistant to training errors than previous works. Extensive experimental results on four benchmark datasets demonstrate the proposed method is superior and more effective than the state-of-the-art subspace clustering methods.

The MillenniumTNG Project: inferring cosmology from galaxy clustering with accelerated N-body scaling and subhalo abundance matching

ABSTRACT We introduce a novel technique for constraining cosmological parameters and galaxy assembly bias using non-linear redshift-space clustering of galaxies. We scale cosmological N-body simulations and insert galaxies with the SubHalo Abundance Matching extended (SHAMe) empirical model to generate over 175 000 clustering measurements spanning all relevant cosmological and SHAMe parameter values. We then build an emulator capable of reproducing the projected galaxy correlation function at the monopole, quadrupole, and hexadecapole level for separations between $0.1\, h^{-1}\, {\rm Mpc}$ and $25\, h^{-1}\, {\rm Mpc}$. We test this approach by using the emulator and Monte Carlo Markov Chain (MCMC) inference to jointly estimate cosmology and assembly bias parameters both for the MTNG740 hydrodynamic simulation and for a semi-analytical model (SAM) galaxy formation built on the MTNG740-DM dark matter-only simulation, obtaining unbiased results for all cosmological parameters. For instance, for MTNG740 and a galaxy number density of $n\sim 0.01 h^{3}\, {\rm Mpc}^{-3}$, we obtain $\sigma _{8}=0.799^{+0.039}_{-0.044}$ and $\Omega _\mathrm{M}h^2= 0.138^{+ 0.025}_{- 0.018}$ (which are within 0.4 and 0.2σ of the MTNG cosmology). For fixed Hubble parameter (h), the constraint becomes $\Omega _\mathrm{M}h^2= 0.137^{+ 0.011}_{- 0.012}$. Our method performs similarly well for the SAM and for other tested sample densities. We almost always recover the true amount of galaxy assembly bias within 1σ. The best constraints are obtained when scales smaller than $2\, h^{-1}\, {\rm Mpc}$ are included, as well as when at least the projected correlation function and the monopole are incorporated. These methods offer a powerful way to constrain cosmological parameters using galaxy surveys.

The MillenniumTNG Project: high-precision predictions for matter clustering and halo statistics

ABSTRACT Cosmological inference with large galaxy surveys requires theoretical models that combine precise predictions for large-scale structure with robust and flexible galaxy formation modelling throughout a sufficiently large cosmic volume. Here, we introduce the millenniumTNG (MTNG) project which combines the hydrodynamical galaxy formation model of illustrisTNG with the large volume of the millennium simulation. Our largest hydrodynamic simulation, covering $(500 \, h^{-1}{\rm Mpc})^3 \simeq (740\, {\rm Mpc})^3$, is complemented by a suite of dark-matter-only simulations with up to 43203 dark matter particles (a mass resolution of $1.32\times 10^8 \, h^{-1}{\rm M}_\odot$) using the fixed-and-paired technique to reduce large-scale cosmic variance. The hydro simulation adds 43203 gas cells, achieving a baryonic mass resolution of $2\times 10^7 \, h^{-1}{\rm M}_\odot$. High time-resolution merger trees and direct light-cone outputs facilitate the construction of a new generation of semi-analytic galaxy formation models that can be calibrated against both the hydro simulation and observation, and then applied to even larger volumes – MTNG includes a flagship simulation with 1.1 trillion dark matter particles and massive neutrinos in a volume of $(3000\, {\rm Mpc})^3$. In this introductory analysis we carry out convergence tests on basic measures of non-linear clustering such as the matter power spectrum, the halo mass function and halo clustering, and we compare simulation predictions to those from current cosmological emulators. We also use our simulations to study matter and halo statistics, such as halo bias and clustering at the baryonic acoustic oscillation scale. Finally we measure the impact of baryonic physics on the matter and halo distributions.

Galaxy clustering from the bottom up: a streaming model emulator I

ABSTRACT In this series of papers, we present a simulation-based model for the non-linear clustering of galaxies based on separate modelling of clustering in real space and velocity statistics. In the first paper, we present an emulator for the real-space correlation function of galaxies, whereas the emulator of the real-to-redshift space mapping based on velocity statistics is presented in the second paper. Here, we show that a neural network emulator for real-space galaxy clustering trained on data extracted from the dark quest suite of N-body simulations achieves sub-per cent accuracies on scales 1 &amp;lt; r &amp;lt; 30 $h^{-1} \, \mathrm{Mpc}$, and better than 3 per cent on scales r &amp;lt; 1 $h^{-1}\, \mathrm{Mpc}$ in predicting the clustering of dark-matter haloes with number density 10−3.5$(h^{-1}\, \mathrm{Mpc})^{-3}$, close to that of SDSS LOWZ-like galaxies. The halo emulator can be combined with a galaxy–halo connection model to predict the galaxy correlation function through the halo model. We demonstrate that we accurately recover the cosmological and galaxy–halo connection parameters when galaxy clustering depends only on the mass of the galaxies’ host halos. Furthermore, the constraining power in σ8 increases by about a factor of 2 when including scales smaller than 5 $h^{-1} \, \mathrm{Mpc}$. However, when mass is not the only property responsible for galaxy clustering, as observed in hydrodynamical or semi-analytic models of galaxy formation, our emulator gives biased constraints on σ8. This bias disappears when small scales (r &amp;lt; 10 $h^{-1}\, \mathrm{Mpc}$) are excluded from the analysis. This shows that a vanilla halo model could introduce biases into the analysis of future data sets.