April 2, 2020

2963 words 14 mins read

Paper Group ANR 259

Synaptic Integration of Spatiotemporal Features with a Dynamic Neuromorphic Processor. Ensemble of Sparse Gaussian Process Experts for Implicit Surface Mapping with Streaming Data. Bundle Adjustment on a Graph Processor. ESRGAN+ : Further Improving Enhanced Super-Resolution Generative Adversarial Network. (Individual) Fairness for $k$-Clustering. A …

Synaptic Integration of Spatiotemporal Features with a Dynamic Neuromorphic Processor


Title	Synaptic Integration of Spatiotemporal Features with a Dynamic Neuromorphic Processor
Authors	Mattias Nilsson, Foteini Liwicki, Fredrik Sandin
Abstract	Spiking neurons can perform spatiotemporal feature detection by nonlinear synaptic and dendritic integration of presynaptic spike patterns. Multicompartment models of nonlinear dendrites and related neuromorphic circuit designs enable faithful imitation of such dynamic integration processes, but these approaches are also associated with a relatively high computing cost or circuit size. Here, we investigate synaptic integration of spatiotemporal spike patterns with multiple dynamic synapses on point-neurons in the DYNAP-SE neuromorphic processor, which can offer a complementary resource-efficient, albeit less flexible, approach to feature detection. We investigate how previously proposed excitatory–inhibitory pairs of dynamic synapses can be combined to integrate multiple inputs, and we generalize that concept to a case in which one inhibitory synapse is combined with multiple excitatory synapses. We characterize the resulting delayed excitatory postsynaptic potentials (EPSPs) by measuring and analyzing the membrane potentials of the neuromorphic neuronal circuits. We find that biologically relevant EPSP delays, with variability of order 10 milliseconds per neuron, can be realized in the proposed manner by selecting different synapse combinations, thanks to device mismatch. Based on these results, we demonstrate that a single point-neuron with dynamic synapses in the DYNAP-SE can respond selectively to presynaptic spikes with a particular spatiotemporal structure, which enables, for instance, visual feature tuning of single neurons.
Tasks
Published	2020-02-12
URL	https://arxiv.org/abs/2002.04924v1
PDF	https://arxiv.org/pdf/2002.04924v1.pdf
PWC	https://paperswithcode.com/paper/synaptic-integration-of-spatiotemporal
Repo
Framework

Ensemble of Sparse Gaussian Process Experts for Implicit Surface Mapping with Streaming Data


Title	Ensemble of Sparse Gaussian Process Experts for Implicit Surface Mapping with Streaming Data
Authors	Johannes A. Stork, Todor Stoyanov
Abstract	Creating maps is an essential task in robotics and provides the basis for effective planning and navigation. In this paper, we learn a compact and continuous implicit surface map of an environment from a stream of range data with known poses. For this, we create and incrementally adjust an ensemble of approximate Gaussian process (GP) experts which are each responsible for a different part of the map. Instead of inserting all arriving data into the GP models, we greedily trade-off between model complexity and prediction error. Our algorithm therefore uses less resources on areas with few geometric features and more where the environment is rich in variety. We evaluate our approach on synthetic and real-world data sets and analyze sensitivity to parameters and measurement noise. The results show that we can learn compact and accurate implicit surface models under different conditions, with a performance comparable to or better than that of exact GP regression with subsampled data.
Tasks
Published	2020-02-12
URL	https://arxiv.org/abs/2002.04911v1
PDF	https://arxiv.org/pdf/2002.04911v1.pdf
PWC	https://paperswithcode.com/paper/ensemble-of-sparse-gaussian-process-experts
Repo
Framework

Bundle Adjustment on a Graph Processor


Title	Bundle Adjustment on a Graph Processor
Authors	Joseph Ortiz, Mark Pupilli, Stefan Leutenegger, Andrew J. Davison
Abstract	Graph processors such as Graphcore’s Intelligence Processing Unit (IPU) are part of the major new wave of novel computer architecture for AI, and have a general design with massively parallel computation, distributed on-chip memory and very high inter-core communication bandwidth which allows breakthrough performance for message passing algorithms on arbitrary graphs. We show for the first time that the classical computer vision problem of bundle adjustment (BA) can be solved extremely fast on a graph processor using Gaussian Belief Propagation. Our simple but fully parallel implementation uses the 1216 cores on a single IPU chip to, for instance, solve a real BA problem with 125 keyframes and 1919 points in under 40ms, compared to 1450ms for the Ceres CPU library. Further code optimisation will surely increase this difference on static problems, but we argue that the real promise of graph processing is for flexible in-place optimisation of general, dynamically changing factor graphs representing Spatial AI problems. We give indications of this with experiments showing the ability of GBP to efficiently solve incremental SLAM problems, and deal with robust cost functions and different types of factors.
Tasks
Published	2020-03-06
URL	https://arxiv.org/abs/2003.03134v2
PDF	https://arxiv.org/pdf/2003.03134v2.pdf
PWC	https://paperswithcode.com/paper/bundle-adjustment-on-a-graph-processor
Repo
Framework

ESRGAN+ : Further Improving Enhanced Super-Resolution Generative Adversarial Network


Title	ESRGAN+ : Further Improving Enhanced Super-Resolution Generative Adversarial Network
Authors	Nathanaël Carraz Rakotonirina, Andry Rasoanaivo
Abstract	Enhanced Super-Resolution Generative Adversarial Network (ESRGAN) is a perceptual-driven approach for single image super resolution that is able to produce photorealistic images. Despite the visual quality of these generated images, there is still room for improvement. In this fashion, the model is extended to further improve the perceptual quality of the images. We have designed a novel block to replace the one used by the original ESRGAN. Moreover, we introduce noise inputs to the generator network in order to exploit stochastic variation. The resulting images present more realistic textures.
Tasks	Image Super-Resolution, Super-Resolution
Published	2020-01-21
URL	https://arxiv.org/abs/2001.08073v1
PDF	https://arxiv.org/pdf/2001.08073v1.pdf
PWC	https://paperswithcode.com/paper/esrgan-further-improving-enhanced-super
Repo
Framework

(Individual) Fairness for $k$-Clustering


Title	(Individual) Fairness for $k$-Clustering
Authors	Sepideh Mahabadi, Ali Vakilian
Abstract	We give a local search based algorithm for $k$-median ($k$-means) clustering from the perspective of individual fairness. More precisely, for a point $x$ in a point set $P$ of size $n$, let $r(x)$ be the minimum radius such that the ball of radius $r(x)$ centered at $x$ has at least $n/k$ points from $P$. Intuitively, if a set of $k$ random points are chosen from $P$ as centers, every point $x\in P$ expects to have a center within radius $r(x)$. An individually fair clustering provides such a guarantee for every point $x\in P$. This notion of fairness was introduced in [Jung et al., 2019] where they showed how to get an approximately feasible $k$-clustering with respect to this fairness condition. In this work, we show how to get an approximately optimal such fair $k$-clustering. The $k$-median ($k$-means) cost of our solution is within a constant factor of the cost of an optimal fair $k$-clustering, and our solution approximately satisfies the fairness condition (also within a constant factor). Further, we complement our theoretical bounds with empirical evaluation.
Tasks
Published	2020-02-17
URL	https://arxiv.org/abs/2002.06742v1
PDF	https://arxiv.org/pdf/2002.06742v1.pdf
PWC	https://paperswithcode.com/paper/individual-fairness-for-k-clustering
Repo
Framework

Assessing the Memory Ability of Recurrent Neural Networks


Title	Assessing the Memory Ability of Recurrent Neural Networks
Authors	Cheng Zhang, Qiuchi Li, Lingyu Hua, Dawei Song
Abstract	It is known that Recurrent Neural Networks (RNNs) can remember, in their hidden layers, part of the semantic information expressed by a sequence (e.g., a sentence) that is being processed. Different types of recurrent units have been designed to enable RNNs to remember information over longer time spans. However, the memory abilities of different recurrent units are still theoretically and empirically unclear, thus limiting the development of more effective and explainable RNNs. To tackle the problem, in this paper, we identify and analyze the internal and external factors that affect the memory ability of RNNs, and propose a Semantic Euclidean Space to represent the semantics expressed by a sequence. Based on the Semantic Euclidean Space, a series of evaluation indicators are defined to measure the memory abilities of different recurrent units and analyze their limitations. These evaluation indicators also provide a useful guidance to select suitable sequence lengths for different RNNs during training.
Tasks
Published	2020-02-18
URL	https://arxiv.org/abs/2002.07422v1
PDF	https://arxiv.org/pdf/2002.07422v1.pdf
PWC	https://paperswithcode.com/paper/assessing-the-memory-ability-of-recurrent
Repo
Framework

Predicting Neural Network Accuracy from Weights


Title	Predicting Neural Network Accuracy from Weights
Authors	Thomas Unterthiner, Daniel Keysers, Sylvain Gelly, Olivier Bousquet, Ilya Tolstikhin
Abstract	We study the prediction of the accuracy of a neural network given only its weights with the goal of better understanding network training and performance. To do so, we propose a formal setting which frames this task and connects to previous work in this area. We collect (and release) a large dataset of almost 80k convolutional neural networks trained on four image datasets. We demonstrate that strong predictors of accuracy exist. Moreover, they can achieve good predictions while only using simple statistics of the weights. Surprisingly, these predictors are able to rank networks trained on unobserved datasets or using different architectures.
Tasks
Published	2020-02-26
URL	https://arxiv.org/abs/2002.11448v1
PDF	https://arxiv.org/pdf/2002.11448v1.pdf
PWC	https://paperswithcode.com/paper/predicting-neural-network-accuracy-from
Repo
Framework

Optimizing Traffic Lights with Multi-agent Deep Reinforcement Learning and V2X communication


Title	Optimizing Traffic Lights with Multi-agent Deep Reinforcement Learning and V2X communication
Authors	Azhar Hussain, Tong Wang, Cao Jiahua
Abstract	We consider a system to optimize duration of traffic signals using multi-agent deep reinforcement learning and Vehicle-to-Everything (V2X) communication. This system aims at analyzing independent and shared rewards for multi-agents to control duration of traffic lights. A learning agent traffic light gets information along its lanes within a circular V2X coverage. The duration cycles of traffic light are modeled as Markov decision Processes. We investigate four variations of reward functions. The first two are unshared-rewards: based on waiting number, and waiting time of vehicles between two cycles of traffic light. The third and fourth functions are: shared-rewards based on waiting cars, and waiting time for all agents. Each agent has a memory for optimization through target network and prioritized experience replay. We evaluate multi-agents through the Simulation of Urban MObility (SUMO) simulator. The results prove effectiveness of the proposed system to optimize traffic signals and reduce average waiting cars to 41.5 % as compared to the traditional periodic traffic control system.
Tasks
Published	2020-02-23
URL	https://arxiv.org/abs/2002.09853v1
PDF	https://arxiv.org/pdf/2002.09853v1.pdf
PWC	https://paperswithcode.com/paper/optimizing-traffic-lights-with-multi-agent
Repo
Framework

AI Online Filters to Real World Image Recognition


Title	AI Online Filters to Real World Image Recognition
Authors	Hai Xiao, Jin Shang, Mengyuan Huang
Abstract	Deep artificial neural networks, trained with labeled data sets are widely used in numerous vision and robotics applications today. In terms of AI, these are called reflex models, referring to the fact that they do not self-evolve or actively adapt to environmental changes. As demand for intelligent robot control expands to many high level tasks, reinforcement learning and state based models play an increasingly important role. Herein, in computer vision and robotics domain, we study a novel approach to add reinforcement controls onto the image recognition reflex models to attain better overall performance, specifically to a wider environment range beyond what is expected of the task reflex models. Follow a common infrastructure with environment sensing and AI based modeling of self-adaptive agents, we implement multiple types of AI control agents. To the end, we provide comparative results of these agents with baseline, and an insightful analysis of their benefit to improve overall image recognition performance in real world.
Tasks
Published	2020-02-11
URL	https://arxiv.org/abs/2002.08242v1
PDF	https://arxiv.org/pdf/2002.08242v1.pdf
PWC	https://paperswithcode.com/paper/ai-online-filters-to-real-world-image
Repo
Framework

Comparing the Parameter Complexity of Hypernetworks and the Embedding-Based Alternative


Title	Comparing the Parameter Complexity of Hypernetworks and the Embedding-Based Alternative
Authors	Tomer Galanti, Lior Wolf
Abstract	In the context of learning to map an input $I$ to a function $h_I:\mathcal{X}\to \mathbb{R}$, we compare two alternative methods: (i) an embedding-based method, which learns a fixed function in which $I$ is encoded as a conditioning signal $e(I)$ and the learned function takes the form $h_I(x) = q(x,e(I))$, and (ii) hypernetworks, in which the weights $\theta_I$ of the function $h_I(x) = g(x;\theta_I)$ are given by a hypernetwork $f$ as $\theta_I=f(I)$. We extend the theory of~\cite{devore} and provide a lower bound on the complexity of neural networks as function approximators, i.e., the number of trainable parameters. This extension, eliminates the requirements for the approximation method to be robust. Our results are then used to compare the complexities of $q$ and $g$, showing that under certain conditions and when letting the functions $e$ and $f$ be as large as we wish, $g$ can be smaller than $q$ by orders of magnitude. In addition, we show that for typical assumptions on the function to be approximated, the overall number of trainable parameters in a hypernetwork is smaller by orders of magnitude than the number of trainable parameters of a standard neural network and an embedding method.
Tasks
Published	2020-02-23
URL	https://arxiv.org/abs/2002.10006v1
PDF	https://arxiv.org/pdf/2002.10006v1.pdf
PWC	https://paperswithcode.com/paper/comparing-the-parameter-complexity-of
Repo
Framework

Robustness of Bayesian Neural Networks to Gradient-Based Attacks


Title	Robustness of Bayesian Neural Networks to Gradient-Based Attacks
Authors	Ginevra Carbone, Matthew Wicker, Luca Laurenti, Andrea Patane, Luca Bortolussi, Guido Sanguinetti
Abstract	Vulnerability to adversarial attacks is one of the principal hurdles to the adoption of deep learning in safety-critical applications. Despite significant efforts, both practical and theoretical, the problem remains open. In this paper, we analyse the geometry of adversarial attacks in the large-data, overparametrized limit for Bayesian Neural Networks (BNNs). We show that, in the limit, vulnerability to gradient-based attacks arises as a result of degeneracy in the data distribution, i.e., when the data lies on a lower-dimensional submanifold of the ambient space. As a direct consequence, we demonstrate that in the limit BNN posteriors are robust to gradient-based adversarial attacks. Experimental results on the MNIST and Fashion MNIST datasets with BNNs trained with Hamiltonian Monte Carlo and Variational Inference support this line of argument, showing that BNNs can display both high accuracy and robustness to gradient based adversarial attacks.
Tasks
Published	2020-02-11
URL	https://arxiv.org/abs/2002.04359v2
PDF	https://arxiv.org/pdf/2002.04359v2.pdf
PWC	https://paperswithcode.com/paper/robustness-of-bayesian-neural-networks-to
Repo
Framework

Keep Doing What Worked: Behavioral Modelling Priors for Offline Reinforcement Learning


Title	Keep Doing What Worked: Behavioral Modelling Priors for Offline Reinforcement Learning
Authors	Noah Y. Siegel, Jost Tobias Springenberg, Felix Berkenkamp, Abbas Abdolmaleki, Michael Neunert, Thomas Lampe, Roland Hafner, Nicolas Heess, Martin Riedmiller
Abstract	Off-policy reinforcement learning algorithms promise to be applicable in settings where only a fixed data-set (batch) of environment interactions is available and no new experience can be acquired. This property makes these algorithms appealing for real world problems such as robot control. In practice, however, standard off-policy algorithms fail in the batch setting for continuous control. In this paper, we propose a simple solution to this problem. It admits the use of data generated by arbitrary behavior policies and uses a learned prior – the advantage-weighted behavior model (ABM) – to bias the RL policy towards actions that have previously been executed and are likely to be successful on the new task. Our method can be seen as an extension of recent work on batch-RL that enables stable learning from conflicting data-sources. We find improvements on competitive baselines in a variety of RL tasks – including standard continuous control benchmarks and multi-task learning for simulated and real-world robots.
Tasks	Continuous Control, Multi-Task Learning
Published	2020-02-19
URL	https://arxiv.org/abs/2002.08396v2
PDF	https://arxiv.org/pdf/2002.08396v2.pdf
PWC	https://paperswithcode.com/paper/keep-doing-what-worked-behavioral-modelling
Repo
Framework

Modeling of Pruning Techniques for Deep Neural Networks Simplification


Title	Modeling of Pruning Techniques for Deep Neural Networks Simplification
Authors	Morteza Mousa Pasandi, Mohsen Hajabdollahi, Nader Karimi, Shadrokh Samavi
Abstract	Convolutional Neural Networks (CNNs) suffer from different issues, such as computational complexity and the number of parameters. In recent years pruning techniques are employed to reduce the number of operations and model size in CNNs. Different pruning methods are proposed, which are based on pruning the connections, channels, and filters. Various techniques and tricks accompany pruning methods, and there is not a unifying framework to model all the pruning methods. In this paper pruning methods are investigated, and a general model which is contained the majority of pruning techniques is proposed. The advantages and disadvantages of the pruning methods can be identified, and all of them can be summarized under this model. The final goal of this model is to provide a general approach for all of the pruning methods with different structures and applications.
Tasks
Published	2020-01-13
URL	https://arxiv.org/abs/2001.04062v1
PDF	https://arxiv.org/pdf/2001.04062v1.pdf
PWC	https://paperswithcode.com/paper/modeling-of-pruning-techniques-for-deep
Repo
Framework

Conservative Exploration in Reinforcement Learning


Title	Conservative Exploration in Reinforcement Learning
Authors	Evrard Garcelon, Mohammad Ghavamzadeh, Alessandro Lazaric, Matteo Pirotta
Abstract	While learning in an unknown Markov Decision Process (MDP), an agent should trade off exploration to discover new information about the MDP, and exploitation of the current knowledge to maximize the reward. Although the agent will eventually learn a good or optimal policy, there is no guarantee on the quality of the intermediate policies. This lack of control is undesired in real-world applications where a minimum requirement is that the executed policies are guaranteed to perform at least as well as an existing baseline. In this paper, we introduce the notion of conservative exploration for average reward and finite horizon problems. We present two optimistic algorithms that guarantee (w.h.p.) that the conservative constraint is never violated during learning. We derive regret bounds showing that being conservative does not hinder the learning ability of these algorithms.
Tasks
Published	2020-02-08
URL	https://arxiv.org/abs/2002.03218v1
PDF	https://arxiv.org/pdf/2002.03218v1.pdf
PWC	https://paperswithcode.com/paper/conservative-exploration-in-reinforcement
Repo
Framework

MRRC: Multiple Role Representation Crossover Interpretation for Image Captioning With R-CNN Feature Distribution Composition (FDC)


Title	MRRC: Multiple Role Representation Crossover Interpretation for Image Captioning With R-CNN Feature Distribution Composition (FDC)
Authors	Chiranjib Sur
Abstract	While image captioning through machines requires structured learning and basis for interpretation, improvement requires multiple context understanding and processing in a meaningful way. This research will provide a novel concept for context combination and will impact many applications to deal visual features as an equivalence of descriptions of objects, activities and events. There are three components of our architecture: Feature Distribution Composition (FDC) Layer Attention, Multiple Role Representation Crossover (MRRC) Attention Layer and the Language Decoder. FDC Layer Attention helps in generating the weighted attention from RCNN features, MRRC Attention Layer acts as intermediate representation processing and helps in generating the next word attention, while Language Decoder helps in estimation of the likelihood for the next probable word in the sentence. We demonstrated effectiveness of FDC, MRRC, regional object feature attention and reinforcement learning for effective learning to generate better captions from images. The performance of our model enhanced previous performances by 35.3% and created a new standard and theory for representation generation based on logic, better interpretability and contexts.
Tasks	Image Captioning
Published	2020-02-15
URL	https://arxiv.org/abs/2002.06436v1
PDF	https://arxiv.org/pdf/2002.06436v1.pdf
PWC	https://paperswithcode.com/paper/mrrc-multiple-role-representation-crossover
Repo
Framework