no code implementations • 25 Mar 2024 • Attila Lischka, Jiaming Wu, Rafael Basso, Morteza Haghir Chehreghani, Balázs Kulcsár
Furthermore, we propose ensembles of different sparsification levels allowing models to focus on the most promising parts while also allowing information flow between all nodes of a TSP instance.
no code implementations • 11 Mar 2024 • Deepthi Pathare, Leo Laine, Morteza Haghir Chehreghani
We develop a deep reinforcement learning framework for tactical decision making in an autonomous truck, specifically for Adaptive Cruise Control (ACC) and lane change maneuvers in a highway scenario.
no code implementations • 10 Feb 2024 • Hannes Nilsson, Rikard Johansson, Niklas Åkerblom, Morteza Haghir Chehreghani
We propose a novel framework for contextual multi-armed bandits based on tree ensembles.
no code implementations • 5 Feb 2024 • Linus Aronsson, Morteza Haghir Chehreghani
Correlation clustering is a powerful unsupervised learning paradigm that supports positive and negative similarities.
no code implementations • 20 Dec 2023 • Jack Sandberg, Niklas Åkerblom, Morteza Haghir Chehreghani
We consider a combinatorial Gaussian process semi-bandit problem with time-varying arm availability.
no code implementations • 21 Aug 2023 • Arman Rahbar, Niklas Åkerblom, Morteza Haghir Chehreghani
In this paper, we provide a novel formulation of the online decision making problem based on combinatorial multi-armed bandits and take the (possibly stochastic) cost of performing tests into account.
no code implementations • 3 May 2023 • Arman Rahbar, Ziyu Ye, Yuxin Chen, Morteza Haghir Chehreghani
Specifically, we employ a surrogate information acquisition function based on adaptive submodularity to actively query feature values with a minimal cost, while using a posterior sampling scheme to maintain a low regret for online prediction.
no code implementations • 6 Apr 2023 • Peter Samoaa, Linus Aronsson, Antonio Longa, Philipp Leitner, Morteza Haghir Chehreghani
Then, we convert the tree representation of the source code to a Flow Augmented-AST graph (FA-AST) representation.
2 code implementations • 30 Mar 2023 • Hampus Gummesson Svensson, Christian Tyrchan, Ola Engkvist, Morteza Haghir Chehreghani
Deep learning-based approaches for generating novel drug molecules with specific properties have gained a lot of interest in the last few years.
no code implementations • 27 Mar 2023 • Ebrahim Balouji, Jonas Sjöblom, Nikolce Murgovski, Morteza Haghir Chehreghani
Finally, the last model is based on two parallel At-LSTMs, where similarly, each At-LSTM predicts time and distance separately through fully connected layers.
no code implementations • 20 Feb 2023 • Linus Aronsson, Morteza Haghir Chehreghani
Correlation clustering is a well-known unsupervised learning setting that deals with positive and negative pairwise similarities.
no code implementations • 17 Jan 2023 • Niklas Åkerblom, Morteza Haghir Chehreghani
In this work, we address the problem of long-distance navigation for battery electric vehicles (BEVs), where one or more charging sessions are required to reach the intended destination.
no code implementations • 28 Oct 2022 • Tobias Lindroth, Axel Svensson, Niklas Åkerblom, Mitra Pourabdollah, Morteza Haghir Chehreghani
One way to mitigate these issues is by performing battery thermal preconditioning, which increases the energy efficiency of the battery.
no code implementations • 25 Aug 2022 • Hazem Peter Samoaa, Antonio Longa, Mazen Mohamad, Morteza Haghir Chehreghani, Philipp Leitner
TEP-GNN uses FA-ASTs, or flow-augmented ASTs, as a graph-based code representation approach, and predicts test execution times using a powerful graph neural network (GNN) deep learning model.
no code implementations • 4 Jul 2022 • Hampus Gummesson Svensson, Esben Jannik Bjerrum, Christian Tyrchan, Ola Engkvist, Morteza Haghir Chehreghani
Recent developments in artificial intelligence and automation support a new drug design paradigm: autonomous drug design.
no code implementations • 16 Jun 2022 • Fazeleh Hoseini, Niklas Åkerblom, Morteza Haghir Chehreghani
Bottleneck identification is a challenging task in network analysis, especially when the network is not fully specified.
no code implementations • 4 Mar 2022 • Federica Comuni, Christopher Mészáros, Niklas Åkerblom, Morteza Haghir Chehreghani
To address the first challenge, passive learning of driver behavior, we investigate non-recurrent architectures such as self-attention models and convolutional neural networks with joint recurrence plots (JRP), and compare them with recurrent models.
1 code implementation • 21 Jan 2022 • Balazs Varga, Balazs Kulcsar, Morteza Haghir Chehreghani
The role of the target network is overtaken by the control input, which also exploits the temporal dependency of samples (opposed to a randomized memory buffer).
no code implementations • 3 Nov 2021 • Niklas Åkerblom, Yuxin Chen, Morteza Haghir Chehreghani
In order to learn the model parameters, we develop an online learning framework and investigate several exploration strategies such as Thompson Sampling and Upper Confidence Bound.
no code implementations • 25 Oct 2021 • Morteza Haghir Chehreghani
Several clustering methods (e. g., Normalized Cut and Ratio Cut) divide the Min Cut cost function by a cluster dependent factor (e. g., the size or the degree of the clusters), in order to yield a more balanced partitioning.
no code implementations • 17 Sep 2021 • Niklas Åkerblom, Fazeleh Sadat Hoseini, Morteza Haghir Chehreghani
In this paper, we study bottleneck identification in networks via extracting minimax paths.
no code implementations • 6 Aug 2021 • Sanna Jarl, Linus Aronsson, Sadegh Rahrovani, Morteza Haghir Chehreghani
In this study, we develop a generic active learning framework to annotate driving trajectory time series data.
1 code implementation • 19 Jul 2021 • Balázs Varga, Balázs Kulcsár, Morteza Haghir Chehreghani
This paper presents a constrained policy gradient algorithm.
no code implementations • 12 Jan 2021 • Victor Eberstein, Jonas Sjöblom, Nikolce Murgovski, Morteza Haghir Chehreghani
In this paper, we present a unified framework for trip destination prediction in an online setting, which is suitable for both online training and online prediction.
no code implementations • 25 Sep 2020 • Fazeleh S. Hoseini, Sadegh Rahrovani, Morteza Haghir Chehreghani
The development of autonomous vehicles requires having access to a large amount of data in the concerning driving scenarios.
no code implementations • 22 Sep 2020 • John Daniel Bossér, Erik Sörstadius, Morteza Haghir Chehreghani
v) We investigate how active learning with neural networks can benefit from pseudo-labels as proxies for actual labels.
no code implementations • 28 Jul 2020 • Andreas Demetriou, Henrik Alfsvåg, Sadegh Rahrovani, Morteza Haghir Chehreghani
Second, we develop an architecture based on Recurrent Autoencoder with GANs to obviate the variable length issue, wherein we train a GAN to learn/generate the latent representations of original trajectories.
no code implementations • 22 Jul 2020 • Carl Johnell, Morteza Haghir Chehreghani
We study Frank-Wolfe algorithms - standard, pairwise, and away-steps - for efficient optimization of Dominant Set Clustering.
no code implementations • 26 May 2020 • Fazeleh Sadat Hoseini, Morteza Haghir Chehreghani
Minimax distance measure extracts the underlying patterns and manifolds in an unsupervised manner.
no code implementations • 30 Mar 2020 • Arman Rahbar, Ashkan Panahi, Chiranjib Bhattacharyya, Devdatt Dubhashi, Morteza Haghir Chehreghani
Knowledge transfer is shown to be a very successful technique for training neural classifiers: together with the ground truth data, it uses the "privileged information" (PI) obtained by a "teacher" network to train a "student" network.
1 code implementation • 27 Mar 2020 • Ali Samadzadeh, Fatemeh Sadat Tabatabaei Far, Ali Javadi, Ahmad Nickabadi, Morteza Haghir Chehreghani
Spiking neural networks (SNNs) can be used in low-power and embedded systems (such as emerging neuromorphic chips) due to their event-based nature.
Ranked #1 on Image Classification on N-MNIST
no code implementations • 3 Mar 2020 • Niklas Åkerblom, Yuxin Chen, Morteza Haghir Chehreghani
In order to learn the model parameters, we develop an online learning framework and investigate several exploration strategies such as Thompson Sampling and Upper Confidence Bound.
no code implementations • 18 Feb 2020 • Morteza Haghir Chehreghani, Mostafa Haghir Chehreghani
We propose a hierarchical correlation clustering method that extends the well-known correlation clustering to produce hierarchical clusters applicable to both positive and negative pairwise dissimilarities.
no code implementations • 24 Jun 2019 • Claes Strannegård, Herman Carlström, Niklas Engsner, Fredrik Mäkeläinen, Filip Slottner Seholm, Morteza Haghir Chehreghani
We present a deep neural-network model for lifelong learning inspired by several forms of neuroplasticity.
no code implementations • 13 May 2019 • Arman Rahbar, Emilio Jorge, Devdatt Dubhashi, Morteza Haghir Chehreghani
The approximated representations induced by these kernels are fed to the neural network and the optimization and generalization properties of the final model are evaluated and compared.
no code implementations • 27 Apr 2019 • Morteza Haghir Chehreghani
We investigate the use of Minimax distances to extract in a nonparametric way the features that capture the unknown underlying patterns and structures in the data.
no code implementations • 9 Mar 2019 • Arman Rahbar, Ashkan Panahi, Morteza Haghir Chehreghani, Devdatt Dubhashi, Hamid Krim
We develop a novel theoretical framework for understating OT schemes respecting a class structure.
no code implementations • 25 Dec 2018 • Yuxin Chen, Morteza Haghir Chehreghani
We propose a novel approach for trip prediction by analyzing user's trip histories.
no code implementations • 21 Dec 2018 • Morteza Haghir Chehreghani, Mostafa Haghir Chehreghani
Then, to address the model selection problem, we study the aggregation of different dendrogram-based distances respectively in solution space and in representation space in the spirit of deep representations.
no code implementations • 20 Dec 2018 • Morteza Haghir Chehreghani
Standard agglomerative clustering suggests establishing a new reliable linkage at every step.
no code implementations • 16 Mar 2017 • Yuxin Chen, Jean-Michel Renders, Morteza Haghir Chehreghani, Andreas Krause
We consider the optimal value of information (VoI) problem, where the goal is to sequentially select a set of tests with a minimal cost, so that one can efficiently make the best decision based on the observed outcomes.