Alert button
Picture for Nikolaos Passalis

Nikolaos Passalis

Alert button

Non-negative isomorphic neural networks for photonic neuromorphic accelerators

Oct 02, 2023
Manos Kirtas, Nikolaos Passalis, Nikolaos Pleros, Anastasios Tefas

Neuromorphic photonic accelerators are becoming increasingly popular, since they can significantly improve computation speed and energy efficiency, leading to femtojoule per MAC efficiency. However, deploying existing DL models on such platforms is not trivial, since a great range of photonic neural network architectures relies on incoherent setups and power addition operational schemes that cannot natively represent negative quantities. This results in additional hardware complexity that increases cost and reduces energy efficiency. To overcome this, we can train non-negative neural networks and potentially exploit the full range of incoherent neuromorphic photonic capabilities. However, existing approaches cannot achieve the same level of accuracy as their regular counterparts, due to training difficulties, as also recent evidence suggests. To this end, we introduce a methodology to obtain the non-negative isomorphic equivalents of regular neural networks that meet requirements of neuromorphic hardware, overcoming the aforementioned limitations. Furthermore, we also introduce a sign-preserving optimization approach that enables training of such isomorphic networks in a non-negative manner.

Viaarxiv icon

Multiplicative update rules for accelerating deep learning training and increasing robustness

Jul 14, 2023
Manos Kirtas, Nikolaos Passalis, Anastasios Tefas

Figure 1 for Multiplicative update rules for accelerating deep learning training and increasing robustness
Figure 2 for Multiplicative update rules for accelerating deep learning training and increasing robustness
Figure 3 for Multiplicative update rules for accelerating deep learning training and increasing robustness
Figure 4 for Multiplicative update rules for accelerating deep learning training and increasing robustness

Even nowadays, where Deep Learning (DL) has achieved state-of-the-art performance in a wide range of research domains, accelerating training and building robust DL models remains a challenging task. To this end, generations of researchers have pursued to develop robust methods for training DL architectures that can be less sensitive to weight distributions, model architectures and loss landscapes. However, such methods are limited to adaptive learning rate optimizers, initialization schemes, and clipping gradients without investigating the fundamental rule of parameters update. Although multiplicative updates have contributed significantly to the early development of machine learning and hold strong theoretical claims, to best of our knowledge, this is the first work that investigate them in context of DL training acceleration and robustness. In this work, we propose an optimization framework that fits to a wide range of optimization algorithms and enables one to apply alternative update rules. To this end, we propose a novel multiplicative update rule and we extend their capabilities by combining it with a traditional additive update term, under a novel hybrid update method. We claim that the proposed framework accelerates training, while leading to more robust models in contrast to traditionally used additive update rule and we experimentally demonstrate their effectiveness in a wide range of task and optimization methods. Such tasks ranging from convex and non-convex optimization to difficult image classification benchmarks applying a wide range of traditionally used optimization methods and Deep Neural Network (DNN) architectures.

Viaarxiv icon

Variational Voxel Pseudo Image Tracking

Feb 12, 2023
Illia Oleksiienko, Paraskevi Nousi, Nikolaos Passalis, Anastasios Tefas, Alexandros Iosifidis

Figure 1 for Variational Voxel Pseudo Image Tracking
Figure 2 for Variational Voxel Pseudo Image Tracking
Figure 3 for Variational Voxel Pseudo Image Tracking

Uncertainty estimation is an important task for critical problems, such as robotics and autonomous driving, because it allows creating statistically better perception models and signaling the model's certainty in its predictions to the decision method or a human supervisor. In this paper, we propose a Variational Neural Network-based version of a Voxel Pseudo Image Tracking (VPIT) method for 3D Single Object Tracking. The Variational Feature Generation Network of the proposed Variational VPIT computes features for target and search regions and the corresponding uncertainties, which are later combined using an uncertainty-aware cross-correlation module in one of two ways: by computing similarity between the corresponding uncertainties and adding it to the regular cross-correlation values, or by penalizing the uncertain feature channels to increase influence of the certain features. In experiments, we show that both methods improve tracking performance, while penalization of uncertain features provides the best uncertainty quality.

* 5 pages, 2 figures, 1 table 
Viaarxiv icon

A Novel Dataset for Evaluating and Alleviating Domain Shift for Human Detection in Agricultural Fields

Sep 27, 2022
Paraskevi Nousi, Emmanouil Mpampis, Nikolaos Passalis, Ole Green, Anastasios Tefas

Figure 1 for A Novel Dataset for Evaluating and Alleviating Domain Shift for Human Detection in Agricultural Fields
Figure 2 for A Novel Dataset for Evaluating and Alleviating Domain Shift for Human Detection in Agricultural Fields
Figure 3 for A Novel Dataset for Evaluating and Alleviating Domain Shift for Human Detection in Agricultural Fields
Figure 4 for A Novel Dataset for Evaluating and Alleviating Domain Shift for Human Detection in Agricultural Fields

In this paper we evaluate the impact of domain shift on human detection models trained on well known object detection datasets when deployed on data outside the distribution of the training set, as well as propose methods to alleviate such phenomena based on the available annotations from the target domain. Specifically, we introduce the OpenDR Humans in Field dataset, collected in the context of agricultural robotics applications, using the Robotti platform, allowing for quantitatively measuring the impact of domain shift in such applications. Furthermore, we examine the importance of manual annotation by evaluating three distinct scenarios concerning the training data: a) only negative samples, i.e., no depicted humans, b) only positive samples, i.e., only images which contain humans, and c) both negative and positive samples. Our results indicate that good performance can be achieved even when using only negative samples, if additional consideration is given to the training process. We also find that positive samples increase performance especially in terms of better localization. The dataset is publicly available for download at https://github.com/opendr-eu/datasets.

Viaarxiv icon

MLGWSC-1: The first Machine Learning Gravitational-Wave Search Mock Data Challenge

Sep 22, 2022
Marlin B. Schäfer, Ondřej Zelenka, Alexander H. Nitz, He Wang, Shichao Wu, Zong-Kuan Guo, Zhoujian Cao, Zhixiang Ren, Paraskevi Nousi, Nikolaos Stergioulas, Panagiotis Iosif, Alexandra E. Koloniari, Anastasios Tefas, Nikolaos Passalis, Francesco Salemi, Gabriele Vedovato, Sergey Klimenko, Tanmaya Mishra, Bernd Brügmann, Elena Cuoco, E. A. Huerta, Chris Messenger, Frank Ohme

Figure 1 for MLGWSC-1: The first Machine Learning Gravitational-Wave Search Mock Data Challenge
Figure 2 for MLGWSC-1: The first Machine Learning Gravitational-Wave Search Mock Data Challenge
Figure 3 for MLGWSC-1: The first Machine Learning Gravitational-Wave Search Mock Data Challenge
Figure 4 for MLGWSC-1: The first Machine Learning Gravitational-Wave Search Mock Data Challenge

We present the results of the first Machine Learning Gravitational-Wave Search Mock Data Challenge (MLGWSC-1). For this challenge, participating groups had to identify gravitational-wave signals from binary black hole mergers of increasing complexity and duration embedded in progressively more realistic noise. The final of the 4 provided datasets contained real noise from the O3a observing run and signals up to a duration of 20 seconds with the inclusion of precession effects and higher order modes. We present the average sensitivity distance and runtime for the 6 entered algorithms derived from 1 month of test data unknown to the participants prior to submission. Of these, 4 are machine learning algorithms. We find that the best machine learning based algorithms are able to achieve up to 95% of the sensitive distance of matched-filtering based production analyses for simulated Gaussian noise at a false-alarm rate (FAR) of one per month. In contrast, for real noise, the leading machine learning search achieved 70%. For higher FARs the differences in sensitive distance shrink to the point where select machine learning submissions outperform traditional search algorithms at FARs $\geq 200$ per month on some datasets. Our results show that current machine learning search algorithms may already be sensitive enough in limited parameter regions to be useful for some production settings. To improve the state-of-the-art, machine learning algorithms need to reduce the false-alarm rates at which they are capable of detecting signals and extend their validity to regions of parameter space where modeled searches are computationally expensive to run. Based on our findings we compile a list of research areas that we believe are the most important to elevate machine learning searches to an invaluable tool in gravitational-wave signal detection.

* 25 pages, 6 figures, 4 tables, additional material available at https://github.com/gwastro/ml-mock-data-challenge-1 
Viaarxiv icon

VPIT: Real-time Embedded Single Object 3D Tracking Using Voxel Pseudo Images

Jun 06, 2022
Illia Oleksiienko, Paraskevi Nousi, Nikolaos Passalis, Anastasios Tefas, Alexandros Iosifidis

Figure 1 for VPIT: Real-time Embedded Single Object 3D Tracking Using Voxel Pseudo Images
Figure 2 for VPIT: Real-time Embedded Single Object 3D Tracking Using Voxel Pseudo Images
Figure 3 for VPIT: Real-time Embedded Single Object 3D Tracking Using Voxel Pseudo Images
Figure 4 for VPIT: Real-time Embedded Single Object 3D Tracking Using Voxel Pseudo Images

In this paper, we propose a novel voxel-based 3D single object tracking (3D SOT) method called Voxel Pseudo Image Tracking (VPIT). VPIT is the first method that uses voxel pseudo images for 3D SOT. The input point cloud is structured by pillar-based voxelization, and the resulting pseudo image is used as an input to a 2D-like Siamese SOT method. The pseudo image is created in the Bird's-eye View (BEV) coordinates, and therefore the objects in it have constant size. Thus, only the object rotation can change in the new coordinate system and not the object scale. For this reason, we replace multi-scale search with a multi-rotation search, where differently rotated search regions are compared against a single target representation to predict both position and rotation of the object. Experiments on KITTI Tracking dataset show that VPIT is the fastest 3D SOT method and maintains competitive Success and Precision values. Application of a SOT method in a real-world scenario meets with limitations such as lower computational capabilities of embedded devices and a latency-unforgiving environment, where the method is forced to skip certain data frames if the inference speed is not high enough. We implement a real-time evaluation protocol and show that other methods lose most of their performance on embedded devices, while VPIT maintains its ability to track the object.

* 10 pages, 5 figures, 4 tables. This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible 
Viaarxiv icon

Deep Residual Error and Bag-of-Tricks Learning for Gravitational Wave Surrogate Modeling

Mar 16, 2022
Styliani-Christina Fragkouli, Paraskevi Nousi, Nikolaos Passalis, Panagiotis Iosif, Nikolaos Stergioulas, Anastasios Tefas

Figure 1 for Deep Residual Error and Bag-of-Tricks Learning for Gravitational Wave Surrogate Modeling
Figure 2 for Deep Residual Error and Bag-of-Tricks Learning for Gravitational Wave Surrogate Modeling
Figure 3 for Deep Residual Error and Bag-of-Tricks Learning for Gravitational Wave Surrogate Modeling
Figure 4 for Deep Residual Error and Bag-of-Tricks Learning for Gravitational Wave Surrogate Modeling

Deep learning methods have been employed in gravitational-wave astronomy to accelerate the construction of surrogate waveforms for the inspiral of spin-aligned black hole binaries, among other applications. We demonstrate, that the residual error of an artificial neural network that models the coefficients of the surrogate waveform expansion (especially those of the phase of the waveform) has sufficient structure to be learnable by a second network. Adding this second network, we were able to reduce the maximum mismatch for waveforms in a validation set by more than an order of magnitude. We also explored several other ideas for improving the accuracy of the surrogate model, such as the exploitation of similarities between waveforms, the augmentation of the training set, the dissection of the input space, using dedicated networks per output coefficient and output augmentation. In several cases, small improvements can be observed, but the most significant improvement still comes from the addition of a second network that models the residual error. Since the residual error for more general surrogate waveform models (when e.g. eccentricity is included) may also have a specific structure, one can expect our method to be applicable to cases where the gain in accuracy could lead to significant gains in computational time.

Viaarxiv icon

Non-Linear Spectral Dimensionality Reduction Under Uncertainty

Feb 09, 2022
Firas Laakom, Jenni Raitoharju, Nikolaos Passalis, Alexandros Iosifidis, Moncef Gabbouj

Figure 1 for Non-Linear Spectral Dimensionality Reduction Under Uncertainty
Figure 2 for Non-Linear Spectral Dimensionality Reduction Under Uncertainty
Figure 3 for Non-Linear Spectral Dimensionality Reduction Under Uncertainty
Figure 4 for Non-Linear Spectral Dimensionality Reduction Under Uncertainty

In this paper, we consider the problem of non-linear dimensionality reduction under uncertainty, both from a theoretical and algorithmic perspectives. Since real-world data usually contain measurements with uncertainties and artifacts, the input space in the proposed framework consists of probability distributions to model the uncertainties associated with each sample. We propose a new dimensionality reduction framework, called NGEU, which leverages uncertainty information and directly extends several traditional approaches, e.g., KPCA, MDA/KMFA, to receive as inputs the probability distributions instead of the original data. We show that the proposed NGEU formulation exhibits a global closed-form solution, and we analyze, based on the Rademacher complexity, how the underlying uncertainties theoretically affect the generalization ability of the framework. Empirical results on different datasets show the effectiveness of the proposed framework.

* 10 pages, 3 figures 
Viaarxiv icon

Autoencoder-driven Spiral Representation Learning for Gravitational Wave Surrogate Modelling

Jul 09, 2021
Paraskevi Nousi, Styliani-Christina Fragkouli, Nikolaos Passalis, Panagiotis Iosif, Theocharis Apostolatos, George Pappas, Nikolaos Stergioulas, Anastasios Tefas

Figure 1 for Autoencoder-driven Spiral Representation Learning for Gravitational Wave Surrogate Modelling
Figure 2 for Autoencoder-driven Spiral Representation Learning for Gravitational Wave Surrogate Modelling
Figure 3 for Autoencoder-driven Spiral Representation Learning for Gravitational Wave Surrogate Modelling
Figure 4 for Autoencoder-driven Spiral Representation Learning for Gravitational Wave Surrogate Modelling

Recently, artificial neural networks have been gaining momentum in the field of gravitational wave astronomy, for example in surrogate modelling of computationally expensive waveform models for binary black hole inspiral and merger. Surrogate modelling yields fast and accurate approximations of gravitational waves and neural networks have been used in the final step of interpolating the coefficients of the surrogate model for arbitrary waveforms outside the training sample. We investigate the existence of underlying structures in the empirical interpolation coefficients using autoencoders. We demonstrate that when the coefficient space is compressed to only two dimensions, a spiral structure appears, wherein the spiral angle is linearly related to the mass ratio. Based on this finding, we design a spiral module with learnable parameters, that is used as the first layer in a neural network, which learns to map the input space to the coefficients. The spiral module is evaluated on multiple neural network architectures and consistently achieves better speed-accuracy trade-off than baseline models. A thorough experimental study is conducted and the final result is a surrogate model which can evaluate millions of input parameters in a single forward pass in under 1ms on a desktop GPU, while the mismatch between the corresponding generated waveforms and the ground-truth waveforms is better than the compared baseline methods. We anticipate the existence of analogous underlying structures and corresponding computational gains also in the case of spinning black hole binaries.

Viaarxiv icon

Graph Embedding with Data Uncertainty

Sep 01, 2020
Firas Laakom, Jenni Raitoharju, Nikolaos Passalis, Alexandros Iosifidis, Moncef Gabbouj

Figure 1 for Graph Embedding with Data Uncertainty
Figure 2 for Graph Embedding with Data Uncertainty
Figure 3 for Graph Embedding with Data Uncertainty
Figure 4 for Graph Embedding with Data Uncertainty

spectral-based subspace learning is a common data preprocessing step in many machine learning pipelines. The main aim is to learn a meaningful low dimensional embedding of the data. However, most subspace learning methods do not take into consideration possible measurement inaccuracies or artifacts that can lead to data with high uncertainty. Thus, learning directly from raw data can be misleading and can negatively impact the accuracy. In this paper, we propose to model artifacts in training data using probability distributions; each data point is represented by a Gaussian distribution centered at the original data point and having a variance modeling its uncertainty. We reformulate the Graph Embedding framework to make it suitable for learning from distributions and we study as special cases the Linear Discriminant Analysis and the Marginal Fisher Analysis techniques. Furthermore, we propose two schemes for modeling data uncertainty based on pair-wise distances in an unsupervised and a supervised contexts.

* 20 pages, 4 figures 
Viaarxiv icon