arXiv subjects

Nadav Cohen

Publications and source records attributed to Nadav Cohen.

At least 37 records · Page 2Linked to original sources

arXiv2024

Deep Learning Assisted Inertial Dead Reckoning and Fusion

The interest in mobile platforms across a variety of applications has increased significantly in recent years. One of the reasons is the ability to achieve accurate navigation by using low-cost sensors. To this end, inertial sensors are fused with global navigation satellite systems (GNSS) signals. GNSS outages during platform operation can result in pure inertial navigation, causing the navigation solution to drift. In such situations, periodic trajectories with dedicated algorithms were suggested to mitigate the drift. With periodic dynamics, inertial deep learning approaches can capture the motion more accurately and provide accurate dead-reckoning for drones and mobile robots. In this paper, we propose approaches to extend deep learning-assisted inertial sensing and fusion capabilities during periodic motion. We begin by demonstrating that fusion between GNSS and inertial sensors in periodic trajectories achieves better accuracy compared to straight-line trajectories. Next, we propose an empowered network architecture to accurately regress the change in distance of the platform. Utilizing this network, we drive a hybrid approach for a neural-inertial fusion filter. Finally, we utilize this approach for situations when GNSS is available and show its benefits. A dataset of 337 minutes of data collected from inertial sensors mounted on a mobile robot and a quadrotor is used to evaluate our approaches.

cs.RO↗

arXiv2024

Implicit Bias of Policy Gradient in Linear Quadratic Control: Extrapolation to Unseen Initial States

In modern machine learning, models can often fit training data in numerous ways, some of which perform well on unseen (test) data, while others do not. Remarkably, in such cases gradient descent frequently exhibits an implicit bias that leads to excellent performance on unseen data. This implicit bias was extensively studied in supervised learning, but is far less understood in optimal control (reinforcement learning). There, learning a controller applied to a system via gradient descent is known as policy gradient, and a question of prime importance is the extent to which a learned controller extrapolates to unseen initial states. This paper theoretically studies the implicit bias of policy gradient in terms of extrapolation to unseen initial states. Focusing on the fundamental Linear Quadratic Regulator (LQR) problem, we establish that the extent of extrapolation depends on the degree of exploration induced by the system when commencing from initial states included in training. Experiments corroborate our theory, and demonstrate its conclusions on problems beyond LQR, where systems are non-linear and controllers are neural networks. We hypothesize that real-world optimal control may be greatly improved by developing methods for informed selection of initial states to train on.

cs.LG↗

arXiv2024

Seamless Underwater Navigation with Limited Doppler Velocity Log Measurements

Autonomous Underwater Vehicles (AUVs) commonly utilize an inertial navigation system (INS) and a Doppler velocity log (DVL) for underwater navigation. To that end, their measurements are integrated through a nonlinear filter such as the extended Kalman filter (EKF). The DVL velocity vector estimate depends on retrieving reflections from the seabed, ensuring that at least three out of its four transmitted acoustic beams return successfully. When fewer than three beams are obtained, the DVL cannot provide a velocity update to bind the navigation solution drift. To cope with this challenge, in this paper, we propose a hybrid neural coupled (HNC) approach for seamless AUV navigation in situations of limited DVL measurements. First, we drive an approach to regress two or three missing DVL beams. Then, those beams, together with the measured beams, are incorporated into the EKF. We examined INS/DVL fusion both in loosely and tightly coupled approaches. Our method was trained and evaluated on recorded data from AUV experiments conducted in the Mediterranean Sea on two different occasions. The results illustrate that our proposed method outperforms the baseline loosely and tightly coupled model-based approaches by an average of 96.15%. It also demonstrates superior performance compared to a model-based beam estimator by an average of 12.41% in terms of velocity accuracy for scenarios involving two or three missing beams. Therefore, we demonstrate that our approach offers seamless AUV navigation in situations of limited beam measurements.

cs.RO↗

arXiv2024

Inertial Navigation Meets Deep Learning: A Survey of Current Trends and Future Directions

Inertial sensing is used in many applications and platforms, ranging from day-to-day devices such as smartphones to very complex ones such as autonomous vehicles. In recent years, the development of machine learning and deep learning techniques has increased significantly in the field of inertial sensing and sensor fusion. This is due to the development of efficient computing hardware and the accessibility of publicly available sensor data. These data-driven approaches mainly aim to empower model-based inertial sensing algorithms. To encourage further research in integrating deep learning with inertial navigation and fusion and to leverage their capabilities, this paper provides an in-depth review of deep learning methods for inertial sensing and sensor fusion. We discuss learning methods for calibration and denoising as well as approaches for improving pure inertial navigation and sensor fusion. The latter is done by learning some of the fusion filter parameters. The reviewed approaches are classified by the environment in which the vehicles operate: land, air, and sea. In addition, we analyze trends and future directions in deep learning-based navigation and provide statistical data on commonly used approaches.

cs.RO↗

arXiv2024

Data-Driven Strategies for Coping with Incomplete DVL Measurements

Autonomous underwater vehicles are specialized platforms engineered for deep underwater operations. Critical to their functionality is autonomous navigation, typically relying on an inertial navigation system and a Doppler velocity log. In real-world scenarios, incomplete Doppler velocity log measurements occur, resulting in positioning errors and mission aborts. To cope with such situations, a model and learning approaches were derived. This paper presents a comparative analysis of two cutting-edge deep learning methodologies, namely LiBeamsNet and MissBeamNet, alongside a model-based average estimator. These approaches are evaluated for their efficacy in regressing missing Doppler velocity log beams when two beams are unavailable. In our study, we used data recorded by a DVL mounted on an autonomous underwater vehicle operated in the Mediterranean Sea. We found that both deep learning architectures outperformed model-based approaches by over 16% in velocity prediction accuracy.

cs.RO↗

arXiv2024

What Makes Data Suitable for a Locally Connected Neural Network? A Necessary and Sufficient Condition Based on Quantum Entanglement

The question of what makes a data distribution suitable for deep learning is a fundamental open problem. Focusing on locally connected neural networks (a prevalent family of architectures that includes convolutional and recurrent neural networks as well as local self-attention models), we address this problem by adopting theoretical tools from quantum physics. Our main theoretical result states that a certain locally connected neural network is capable of accurate prediction over a data distribution if and only if the data distribution admits low quantum entanglement under certain canonical partitions of features. As a practical application of this result, we derive a preprocessing method for enhancing the suitability of a data distribution to locally connected neural networks. Experiments with widespread models over various datasets demonstrate our findings. We hope that our use of quantum entanglement will encourage further adoption of tools from physics for formally reasoning about the relation between deep learning and real-world data.

cs.LG↗

arXiv2023

On the Ability of Graph Neural Networks to Model Interactions Between Vertices

Graph neural networks (GNNs) are widely used for modeling complex interactions between entities represented as vertices of a graph. Despite recent efforts to theoretically analyze the expressive power of GNNs, a formal characterization of their ability to model interactions is lacking. The current paper aims to address this gap. Formalizing strength of interactions through an established measure known as separation rank, we quantify the ability of certain GNNs to model interaction between a given subset of vertices and its complement, i.e. between the sides of a given partition of input vertices. Our results reveal that the ability to model interaction is primarily determined by the partition's walk index -- a graph-theoretical characteristic defined by the number of walks originating from the boundary of the partition. Experiments with common GNN architectures corroborate this finding. As a practical application of our theory, we design an edge sparsification algorithm named Walk Index Sparsification (WIS), which preserves the ability of a GNN to model interactions when input edges are removed. WIS is simple, computationally efficient, and in our experiments has markedly outperformed alternative methods in terms of induced prediction accuracy. More broadly, it showcases the potential of improving GNNs by theoretically analyzing the interactions they can model.

cs.LG↗

arXiv2023

Deep Linear Networks for Matrix Completion -- An Infinite Depth Limit

The deep linear network (DLN) is a model for implicit regularization in gradient based optimization of overparametrized learning architectures. Training the DLN corresponds to a Riemannian gradient flow, where the Riemannian metric is defined by the architecture of the network and the loss function is defined by the learning task. We extend this geometric framework, obtaining explicit expressions for the volume form, including the case when the network has infinite depth. We investigate the link between the Riemannian geometry and the training asymptotics for matrix completion with rigorous analysis and numerics. We propose that implicit regularization is a result of bias towards high state space volume.

math.DS↗

arXiv2023

Learning Low Dimensional State Spaces with Overparameterized Recurrent Neural Nets

Overparameterization in deep learning typically refers to settings where a trained neural network (NN) has representational capacity to fit the training data in many ways, some of which generalize well, while others do not. In the case of Recurrent Neural Networks (RNNs), there exists an additional layer of overparameterization, in the sense that a model may exhibit many solutions that generalize well for sequence lengths seen in training, some of which extrapolate to longer sequences, while others do not. Numerous works have studied the tendency of Gradient Descent (GD) to fit overparameterized NNs with solutions that generalize well. On the other hand, its tendency to fit overparameterized RNNs with solutions that extrapolate has been discovered only recently and is far less understood. In this paper, we analyze the extrapolation properties of GD when applied to overparameterized linear RNNs. In contrast to recent arguments suggesting an implicit bias towards short-term memory, we provide theoretical evidence for learning low-dimensional state spaces, which can also model long-term memory. Our result relies on a dynamical characterization which shows that GD (with small step size and near-zero initialization) strives to maintain a certain form of balancedness, as well as on tools developed in the context of the moment problem from statistics (recovery of a probability distribution from its moments). Experiments corroborate our theory, demonstrating extrapolation via learning low-dimensional state spaces with both linear and non-linear RNNs.

cs.LG↗

arXiv2022

Set-Transformer BeamsNet for AUV Velocity Forecasting in Complete DVL Outage Scenarios

Autonomous underwater vehicles (AUVs) are regularly used for deep ocean applications. Commonly, the autonomous navigation task is carried out by a fusion between two sensors: the inertial navigation system and the Doppler velocity log (DVL). The DVL operates by transmitting four acoustic beams to the sea floor, and once reflected back, the AUV velocity vector can be estimated. However, in real-life scenarios, such as an uneven seabed, sea creatures blocking the DVL's view and, roll/pitch maneuvers, the acoustic beams' reflection is resulting in a scenario known as DVL outage. Consequently, a velocity update is not available to bind the inertial solution drift. To cope with such situations, in this paper, we leverage our BeamsNet framework and propose a Set-Transformer-based BeamsNet (ST-BeamsNet) that utilizes inertial data readings and previous DVL velocity measurements to regress the current AUV velocity in case of a complete DVL outage. The proposed approach was evaluated using data from experiments held in the Mediterranean Sea with the Snapir AUV and was compared to a moving average (MA) estimator. Our ST-BeamsNet estimated the AUV velocity vector with an 8.547% speed error, which is 26% better than the MA approach.

cs.RO↗

arXiv2022

LiBeamsNet: AUV Velocity Vector Estimation in Situations of Limited DVL Beam Measurements

Autonomous underwater vehicles (AUVs) are employed for marine applications and can operate in deep underwater environments beyond human reach. A standard solution for the autonomous navigation problem can be obtained by fusing the inertial navigation system and the Doppler velocity log sensor (DVL). The latter measures four beam velocities to estimate the vehicle's velocity vector. In real-world scenarios, the DVL may receive less than three beam velocities if the AUV operates in complex underwater environments. In such conditions, the vehicle's velocity vector could not be estimated leading to a navigation solution drift and in some situations the AUV is required to abort the mission and return to the surface. To circumvent such a situation, in this paper we propose a deep learning framework, LiBeamsNet, that utilizes the inertial data and the partial beam velocities to regress the missing beams in two missing beams scenarios. Once all the beams are obtained, the vehicle's velocity vector can be estimated. The approach performance was validated by sea experiments in the Mediterranean Sea. The results show up to 7.2% speed error in the vehicle's velocity vector estimation in a scenario that otherwise could not provide an estimate.

cs.RO↗

arXiv2022

Implicit Regularization in Hierarchical Tensor Factorization and Deep Convolutional Neural Networks

In the pursuit of explaining implicit regularization in deep learning, prominent focus was given to matrix and tensor factorizations, which correspond to simplified neural networks. It was shown that these models exhibit an implicit tendency towards low matrix and tensor ranks, respectively. Drawing closer to practical deep learning, the current paper theoretically analyzes the implicit regularization in hierarchical tensor factorization, a model equivalent to certain deep convolutional neural networks. Through a dynamical systems lens, we overcome challenges associated with hierarchy, and establish implicit regularization towards low hierarchical tensor rank. This translates to an implicit regularization towards locality for the associated convolutional networks. Inspired by our theory, we design explicit regularization discouraging locality, and demonstrate its ability to improve the performance of modern convolutional networks on non-local tasks, in defiance of conventional wisdom by which architectural changes are needed. Our work highlights the potential of enhancing neural networks via theoretical analysis of their implicit regularization.

cs.LG↗

arXiv2022

BeamsNet: A data-driven Approach Enhancing Doppler Velocity Log Measurements for Autonomous Underwater Vehicle Navigation

Autonomous underwater vehicles (AUV) perform various applications such as seafloor mapping and underwater structure health monitoring. Commonly, an inertial navigation system aided by a Doppler velocity log (DVL) is used to provide the vehicle's navigation solution. In such fusion, the DVL provides the velocity vector of the AUV, which determines the navigation solution's accuracy and helps estimate the navigation states. This paper proposes BeamsNet, an end-to-end deep learning framework to regress the estimated DVL velocity vector that improves the accuracy of the velocity vector estimate, and could replace the model-based approach. Two versions of BeamsNet, differing in their input to the network, are suggested. The first uses the current DVL beam measurements and inertial sensors data, while the other utilizes only DVL data, taking the current and past DVL measurements for the regression process. Both simulation and sea experiments were made to validate the proposed learning approach relative to the model-based approach. Sea experiments were made with the Snapir AUV in the Mediterranean Sea, collecting approximately four hours of DVL and inertial sensor data. Our results show that the proposed approach achieved an improvement of more than 60% in estimating the DVL velocity vector.

cs.RO↗

arXiv2022

On the Implicit Bias of Gradient Descent for Temporal Extrapolation

When using recurrent neural networks (RNNs) it is common practice to apply trained models to sequences longer than those seen in training. This "extrapolating" usage deviates from the traditional statistical learning setup where guarantees are provided under the assumption that train and test distributions are identical. Here we set out to understand when RNNs can extrapolate, focusing on a simple case where the data generating distribution is memoryless. We first show that even with infinite training data, there exist RNN models that interpolate perfectly (i.e., they fit the training data) yet extrapolate poorly to longer sequences. We then show that if gradient descent is used for training, learning will converge to perfect extrapolation under certain assumptions on initialization. Our results complement recent studies on the implicit bias of gradient descent, showing that it plays a key role in extrapolation when learning temporal prediction models.

cs.LG↗

arXiv2022

Semantic Segmentation in Art Paintings

Semantic segmentation is a difficult task even when trained in a supervised manner on photographs. In this paper, we tackle the problem of semantic segmentation of artistic paintings, an even more challenging task because of a much larger diversity in colors, textures, and shapes and because there are no ground truth annotations available for segmentation. We propose an unsupervised method for semantic segmentation of paintings using domain adaptation. Our approach creates a training set of pseudo-paintings in specific artistic styles by using style-transfer on the PASCAL VOC 2012 dataset, and then applies domain confusion between PASCAL VOC 2012 and real paintings. These two steps build on a new dataset we gathered called DRAM (Diverse Realism in Art Movements) composed of figurative art paintings from four movements, which are highly diverse in pattern, color, and geometry. To segment new paintings, we present a composite multi-domain adaptation method that trains on each sub-domain separately and composes their solutions during inference time. Our method provides better segmentation results not only on the specific artistic movements of DRAM, but also on other, unseen ones. We compare our approach to alternative methods and show applications of semantic segmentation in art paintings. The code and models for our approach are publicly available at: https://github.com/Nadavc220/SemanticSegmentationInArtPaintings.

cs.CV↗

arXiv2021

Continuous vs. Discrete Optimization of Deep Neural Networks

Existing analyses of optimization in deep learning are either continuous, focusing on (variants of) gradient flow, or discrete, directly treating (variants of) gradient descent. Gradient flow is amenable to theoretical analysis, but is stylized and disregards computational efficiency. The extent to which it represents gradient descent is an open question in the theory of deep learning. The current paper studies this question. Viewing gradient descent as an approximate numerical solution to the initial value problem of gradient flow, we find that the degree of approximation depends on the curvature around the gradient flow trajectory. We then show that over deep neural networks with homogeneous activations, gradient flow trajectories enjoy favorable curvature, suggesting they are well approximated by gradient descent. This finding allows us to translate an analysis of gradient flow over deep linear neural networks into a guarantee that gradient descent efficiently converges to global minimum almost surely under random initialization. Experiments suggest that over simple deep neural networks, gradient descent with conventional step size is indeed close to gradient flow. We hypothesize that the theory of gradient flows will unravel mysteries behind deep learning.

cs.LG↗

arXiv2021

Implicit Regularization in Tensor Factorization

Recent efforts to unravel the mystery of implicit regularization in deep learning have led to a theoretical focus on matrix factorization -- matrix completion via linear neural network. As a step further towards practical deep learning, we provide the first theoretical analysis of implicit regularization in tensor factorization -- tensor completion via certain type of non-linear neural network. We circumvent the notorious difficulty of tensor problems by adopting a dynamical systems perspective, and characterizing the evolution induced by gradient descent. The characterization suggests a form of greedy low tensor rank search, which we rigorously prove under certain conditions, and empirically demonstrate under others. Motivated by tensor rank capturing the implicit regularization of a non-linear neural network, we empirically explore it as a measure of complexity, and find that it captures the essence of datasets on which neural networks generalize. This leads us to believe that tensor rank may pave way to explaining both implicit regularization in deep learning, and the properties of real-world data translating this implicit regularization to generalization.

cs.LG↗

arXiv2020

Implicit Regularization in Deep Learning May Not Be Explainable by Norms

Mathematically characterizing the implicit regularization induced by gradient-based optimization is a longstanding pursuit in the theory of deep learning. A widespread hope is that a characterization based on minimization of norms may apply, and a standard test-bed for studying this prospect is matrix factorization (matrix completion via linear neural networks). It is an open question whether norms can explain the implicit regularization in matrix factorization. The current paper resolves this open question in the negative, by proving that there exist natural matrix factorization problems on which the implicit regularization drives all norms (and quasi-norms) towards infinity. Our results suggest that, rather than perceiving the implicit regularization via norms, a potentially more useful interpretation is minimization of rank. We demonstrate empirically that this interpretation extends to a certain class of non-linear neural networks, and hypothesize that it may be key to explaining generalization in deep learning.

cs.LG↗