scholarly journals Learning to Follow Directions in Street View

2020 ◽  
Vol 34 (07) ◽  
pp. 11773-11781 ◽  
Author(s):  
Karl Moritz Hermann ◽  
Mateusz Malinowski ◽  
Piotr Mirowski ◽  
Andras Banki-Horvath ◽  
Keith Anderson ◽  
...  
Keyword(s):  
Machine Learning ◽  
Computer Vision ◽  
Reinforcement Learning ◽  
Real World ◽  
Real World Data ◽  
Simulated Environments ◽  
Extensive Analysis ◽  
Street View ◽  
Generalisation Ability ◽  
Real Places

Navigating and understanding the real world remains a key challenge in machine learning and inspires a great variety of research in areas such as language grounding, planning, navigation and computer vision. We propose an instruction-following task that requires all of the above, and which combines the practicality of simulated environments with the challenges of ambiguous, noisy real world data. StreetNav is built on top of Google Street View and provides visually accurate environments representing real places. Agents are given driving instructions which they must learn to interpret in order to successfully navigate in this environment. Since humans equipped with driving instructions can readily navigate in previously unseen cities, we set a high bar and test our trained agents for similar cognitive capabilities. Although deep reinforcement learning (RL) methods are frequently evaluated only on data that closely follow the training distribution, our dataset extends to multiple cities and has a clean train/test separation. This allows for thorough testing of generalisation ability. This paper presents the StreetNav environment and tasks, models that establish strong baselines, and extensive analysis of the task and the trained agents.

scholarly journals Combining Outcome-Based and Preference-Based Matching: A Constrained Priority Mechanism

2021 ◽  
pp. 1-24
Author(s):  
Avidit Acharya ◽  
Kirk Bansak ◽  
Jens Hainmueller
Keyword(s):  
Machine Learning ◽  
Host Country ◽  
Real World ◽  
Test Scores ◽  
Standardized Test ◽  
Market Design ◽  
Standardized Test Scores ◽  
Real World Data ◽  
Refugee Families ◽  
Strategy Proof

Abstract We introduce a constrained priority mechanism that combines outcome-based matching from machine learning with preference-based allocation schemes common in market design. Using real-world data, we illustrate how our mechanism could be applied to the assignment of refugee families to host country locations, and kindergarteners to schools. Our mechanism allows a planner to first specify a threshold $\bar g$ for the minimum acceptable average outcome score that should be achieved by the assignment. In the refugee matching context, this score corresponds to the probability of employment, whereas in the student assignment context, it corresponds to standardized test scores. The mechanism is a priority mechanism that considers both outcomes and preferences by assigning agents (refugee families and students) based on their preferences, but subject to meeting the planner’s specified threshold. The mechanism is both strategy-proof and constrained efficient in that it always generates a matching that is not Pareto dominated by any other matching that respects the planner’s threshold.

scholarly journals How to train your robot with deep reinforcement learning: lessons we have learned

2021 ◽  
pp. 027836492098785
Author(s):  
Julian Ibarz ◽  
Jie Tan ◽  
Chelsea Finn ◽  
Mrinal Kalakrishnan ◽  
Peter Pastor ◽  
...  
Keyword(s):  
Machine Learning ◽  
Reinforcement Learning ◽  
Case Studies ◽  
Real World ◽  
Review Article ◽  
The Real ◽  
Complex Skills ◽  
Real World Learning ◽  
Level Sensor ◽  
Embodied Agent

Deep reinforcement learning (RL) has emerged as a promising approach for autonomously acquiring complex behaviors from low-level sensor observations. Although a large portion of deep RL research has focused on applications in video games and simulated control, which does not connect with the constraints of learning in real environments, deep RL has also demonstrated promise in enabling physical robots to learn complex skills in the real world. At the same time, real-world robotics provides an appealing domain for evaluating such algorithms, as it connects directly to how humans learn: as an embodied agent in the real world. Learning to perceive and move in the real world presents numerous challenges, some of which are easier to address than others, and some of which are often not considered in RL research that focuses only on simulated domains. In this review article, we present a number of case studies involving robotic deep RL. Building off of these case studies, we discuss commonly perceived challenges in deep RL and how they have been addressed in these works. We also provide an overview of other outstanding challenges, many of which are unique to the real-world robotics setting and are not often the focus of mainstream RL research. Our goal is to provide a resource both for roboticists and machine learning researchers who are interested in furthering the progress of deep RL in the real world.

A Survey on Data-driven Network Intrusion Detection

2022 ◽  
Vol 54 (9) ◽  
pp. 1-36
Author(s):  
Dylan Chou ◽  
Meng Jiang
Keyword(s):  
Machine Learning ◽  
Intrusion Detection ◽  
Real World ◽  
Data Driven ◽  
Network Intrusion Detection ◽  
Large Network ◽  
Learning Models ◽  
Simulated Environments ◽  
Network Intrusion ◽  
Machine Learning Models

Data-driven network intrusion detection (NID) has a tendency towards minority attack classes compared to normal traffic. Many datasets are collected in simulated environments rather than real-world networks. These challenges undermine the performance of intrusion detection machine learning models by fitting machine learning models to unrepresentative “sandbox” datasets. This survey presents a taxonomy with eight main challenges and explores common datasets from 1999 to 2020. Trends are analyzed on the challenges in the past decade and future directions are proposed on expanding NID into cloud-based environments, devising scalable models for large network data, and creating labeled datasets collected in real-world networks.

Interactive Learning with Mutual Explanations in Relational Domains

2021 ◽  
pp. 338-354
Author(s):  
Ute Schmid
Keyword(s):  
Machine Learning ◽  
Real World ◽  
Inductive Logic Programming ◽  
Interactive Learning ◽  
Inductive Logic ◽  
Learning System ◽  
Real World Data ◽  
Relational Domains ◽  
Learning Research ◽  
Applications Of Machine Learning

With the growing number of applications of machine learning in complex real-world domains machine learning research has to meet new requirements to deal with the imperfections of real world data and the legal as well as ethical obligations to make classifier decisions transparent and comprehensible. In this contribution, arguments for interpretable and interactive approaches to machine learning are presented. It is argued that visual explanations are often not expressive enough to grasp critical information which relies on relations between different aspects or sub-concepts. Consequently, inductive logic programming (ILP) and the generation of verbal explanations from Prolog rules is advocated. Interactive learning in the context of ILP is illustrated with the Dare2Del system which helps users to manage their digital clutter. It is shown that verbal explanations overcome the explanatory one-way street from AI system to user. Interactive learning with mutual explanations allows the learning system to take into account not only class corrections but also corrections of explanations to guide learning. We propose mutual explanations as a building-block for human-like computing and an important ingredient for human AI partnership.

scholarly journals Using Random Forests on Real-World City Data for Urban Planning in a Visual Semantic Decision Support System

Sensors ◽  
2019 ◽  
Vol 19 (10) ◽  
pp. 2266 ◽  
Author(s):  
Nikolaos Sideris ◽  
Georgios Bardis ◽  
Athanasios Voulodimos ◽  
Georgios Miaoulis ◽  
Djamchid Ghazanfarpour
Keyword(s):  
Machine Learning ◽  
Urban Planning ◽  
Random Forests ◽  
Real World ◽  
Performance Metrics ◽  
World City ◽  
Supervised Machine Learning ◽  
Machine Learning Techniques ◽  
Support Vector ◽  
Real World Data

The constantly increasing amount and availability of urban data derived from varying sources leads to an assortment of challenges that include, among others, the consolidation, visualization, and maximal exploitation prospects of the aforementioned data. A preeminent problem affecting urban planning is the appropriate choice of location to host a particular activity (either commercial or common welfare service) or the correct use of an existing building or empty space. In this paper, we propose an approach to address these challenges availed with machine learning techniques. The proposed system combines, fuses, and merges various types of data from different sources, encodes them using a novel semantic model that can capture and utilize both low-level geometric information and higher level semantic information and subsequently feeds them to the random forests classifier, as well as other supervised machine learning models for comparisons. Our experimental evaluation on multiple real-world data sets comparing the performance of several classifiers (including Feedforward Neural Networks, Support Vector Machines, Bag of Decision Trees, k-Nearest Neighbors and Naïve Bayes), indicated the superiority of Random Forests in terms of the examined performance metrics (Accuracy, Specificity, Precision, Recall, F-measure and G-mean).

Deep Reinforcement Learning-Based Irrigation Scheduling

2020 ◽  
Vol 63 (3) ◽  
pp. 549-556
Author(s):  
Yanxiang Yang ◽  
Jiang Hu ◽  
Dana Porter ◽  
Thomas Marek ◽  
Kevin Heflin ◽  
...  
Keyword(s):  
Machine Learning ◽  
Reinforcement Learning ◽  
Real World ◽  
Weather Conditions ◽  
Irrigation Scheduling ◽  
Water Application ◽  
Time Step ◽  
Net Return ◽  
Crop Growth Stage ◽  
Learning Machine

Highlights Deep reinforcement learning-based irrigation scheduling is proposed to determine the amount of irrigation required at each time step considering soil moisture level, evapotranspiration, forecast precipitation, and crop growth stage. The proposed methodology was compared with traditional irrigation scheduling approaches and some machine learning based scheduling approaches based on simulation. Abstract. Machine learning has been widely applied in many areas, with promising results and large potential. In this article, deep reinforcement learning-based irrigation scheduling is proposed. This approach can automate the irrigation process and can achieve highly precise water application that results in higher simulated net return. Using this approach, the irrigation controller can automatically determine the optimal or near-optimal water application amount. Traditional reinforcement learning can be superior to traditional periodic and threshold-based irrigation scheduling. However, traditional reinforcement learning fails to accurately represent a real-world irrigation environment due to its limited state space. Compared with traditional reinforcement learning, the deep reinforcement learning method can better model a real-world environment based on multi-dimensional observations. Simulations for various weather conditions and crop types show that the proposed deep reinforcement learning irrigation scheduling can increase net return. Keywords: Automated irrigation scheduling, Deep reinforcement learning, Machine learning.

scholarly journals Customized Dictionary Learning for Subdatasets with Fine Granularity

2016 ◽  
Vol 2016 ◽  
pp. 1-13
Author(s):  
Lei Ye ◽  
Can Wang ◽  
Xin Xu ◽  
Hui Qian
Keyword(s):  
Machine Learning ◽  
Computer Vision ◽  
Theoretical Analysis ◽  
Improve Performance ◽  
Real World Data ◽  
Sparse Models ◽  
Learned Dictionary ◽  
Wide Range ◽  
Sparsity Constraints ◽  
The Difference

Sparse models have a wide range of applications in machine learning and computer vision. Using a learned dictionary instead of an “off-the-shelf” one can dramatically improve performance on a particular dataset. However, learning a new one for each subdataset (subject) with fine granularity may be unwarranted or impractical, due to restricted availability subdataset samples and tremendous numbers of subjects. To remedy this, we consider the dictionary customization problem, that is, specializing an existing global dictionary corresponding to the total dataset, with the aid of auxiliary samples obtained from the target subdataset. Inspired by observation and then deduced from theoretical analysis, a regularizer is employed penalizing the difference between the global and the customized dictionary. By minimizing the sum of reconstruction errors of the above regularizer under sparsity constraints, we exploit the characteristics of the target subdataset contained in the auxiliary samples while maintaining the basic sketches stored in the global dictionary. An efficient algorithm is presented and validated with experiments on real-world data.

Sign in / Sign up

Export Citation Format

Share Document