Artificial Intelligence

---

GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond (1904.11492v1)

Yue Cao, Jiarui Xu, Stephen Lin, Fangyun Wei, Han Hu

2019-04-25

The Non-Local Network (NLNet) presents a pioneering approach for capturing long-range dependencies, via aggregating query-specific global context to each query position. However, through a rigorous empirical analysis, we have found that the global contexts modeled by non-local network are almost the same for different query positions within an image. In this paper, we take advantage of this finding to create a simplified network based on a query-independent formulation, which maintains the accuracy of NLNet but with significantly less computation. We further observe that this simplified design shares similar structure with Squeeze-Excitation Network (SENet). Hence we unify them into a three-step general framework for global context modeling. Within the general framework, we design a better instantiation, called the global context (GC) block, which is lightweight and can effectively model the global context. The lightweight property allows us to apply it for multiple layers in a backbone network to construct a global context network (GCNet), which generally outperforms both simplified NLNet and SENet on major benchmarks for various recognition tasks. The code and configurations are released at https://github.com/xvjiarui/GCNet.

Local Relation Networks for Image Recognition (1904.11491v1)

Han Hu, Zheng Zhang, Zhenda Xie, Stephen Lin

2019-04-25

The convolution layer has been the dominant feature extractor in computer vision for years. However, the spatial aggregation in convolution is basically a pattern matching process that applies fixed filters which are inefficient at modeling visual elements with varying spatial distributions. This paper presents a new image feature extractor, called the local relation layer, that adaptively determines aggregation weights based on the compositional relationship of local pixel pairs. With this relational approach, it can composite visual elements into higher-level entities in a more efficient manner that benefits semantic inference. A network built with local relation layers, called the Local Relation Network (LR-Net), is found to provide greater modeling capacity than its counterpart built with regular convolution on large-scale recognition tasks such as ImageNet classification.

Safe Reinforcement Learning with Scene Decomposition for Navigating Complex Urban Environments (1904.11483v1)

Maxime Bouton, Alireza Nakhaei, Kikuo Fujimura, Mykel J. Kochenderfer

2019-04-25

Navigating urban environments represents a complex task for automated vehicles. They must reach their goal safely and efficiently while considering a multitude of traffic participants. We propose a modular decision making algorithm to autonomously navigate intersections, addressing challenges of existing rule-based and reinforcement learning (RL) approaches. We first present a safe RL algorithm relying on a model-checker to ensure safety guarantees. To make the decision strategy robust to perception errors and occlusions, we introduce a belief update technique using a learning based approach. Finally, we use a scene decomposition approach to scale our algorithm to environments with multiple traffic participants. We empirically demonstrate that our algorithm outperforms rule-based methods and reinforcement learning techniques on a complex intersection scenario.

Importance of Copying Mechanism for News Headline Generation (1904.11475v1)

Ilya Gusev

2019-04-25

News headline generation is an essential problem of text summarization because it is constrained, well-defined, and is still hard to solve. Models with a limited vocabulary can not solve it well, as new named entities can appear regularly in the news and these entities often should be in the headline. News articles in morphologically rich languages such as Russian require model modifications due to a large number of possible word forms. This study aims to validate that models with a possibility of copying words from the original article performs better than models without such an option. The proposed model achieves a mean ROUGE score of 23 on the provided test dataset, which is 8 points greater than the result of a similar model without a copying mechanism. Moreover, the resulting model performs better than any known model on the new dataset of Russian news.

Learning a Lattice Planner Control Set for Autonomous Vehicles (1903.02044v2)

Ryan De Iaco, Stephen L. Smith, Krzysztof Czarnecki

2019-03-05

This paper introduces a method to compute a sparse lattice planner control set that is suited to a particular task by learning from a representative dataset of vehicle paths. To do this, we use a scoring measure similar to the Fr'echet distance and propose an algorithm for evaluating a given control set according to the scoring measure. Control actions are then selected from a dense control set according to an objective function that rewards improvements in matching the dataset while also encouraging sparsity. This method is evaluated across several experiments involving real and synthetic datasets, and it is shown to generate smaller control sets when compared to the previous state-of-the-art lattice control set computation technique, with these smaller control sets maintaining a high degree of manoeuvrability in the required task. This results in a planning time speedup of up to 4.31x when using the learned control set over the state-of-the-art computed control set. In addition, we show the learned control sets are better able to capture the driving style of the dataset in terms of path curvature.

Ray Interference: a Source of Plateaus in Deep Reinforcement Learning (1904.11455v1)

Tom Schaul, Diana Borsa, Joseph Modayil, Razvan Pascanu

2019-04-25

Rather than proposing a new method, this paper investigates an issue present in existing learning algorithms. We study the learning dynamics of reinforcement learning (RL), specifically a characteristic coupling between learning and data generation that arises because RL agents control their future data distribution. In the presence of function approximation, this coupling can lead to a problematic type of 'ray interference', characterized by learning dynamics that sequentially traverse a number of performance plateaus, effectively constraining the agent to learn one thing at a time even when learning in parallel is better. We establish the conditions under which ray interference occurs, show its relation to saddle points and obtain the exact learning dynamics in a restricted setting. We characterize a number of its properties and discuss possible remedies.

Reward-Based Deception with Cognitive Bias (1904.11454v1)

Bo Wu, Murat Cubuktepe, Suda Bharadwaj, Ufuk Topcu

2019-04-25

Deception plays a key role in adversarial or strategic interactions for the purpose of self-defence and survival. This paper introduces a general framework and solution to address deception. Most existing approaches for deception consider obfuscating crucial information to rational adversaries with abundant memory and computation resources. In this paper, we consider deceiving adversaries with bounded rationality and in terms of expected rewards. This problem is commonly encountered in many applications especially involving human adversaries. Leveraging the cognitive bias of humans in reward evaluation under stochastic outcomes, we introduce a framework to optimally assign resources of a limited quantity to optimally defend against human adversaries. Modeling such cognitive biases follows the so-called prospect theory from behavioral psychology literature. Then we formulate the resource allocation problem as a signomial program to minimize the defender's cost in an environment modeled as a Markov decision process. We use police patrol hour assignment as an illustrative example and provide detailed simulation results based on real-world data.

Faster and More Accurate Learning with Meta Trace Adaptation (1904.11439v1)

Mingde Zhao, Ian Porada

2019-04-25

Learning speed and accuracy are of universal interest for reinforcement learning problems. In this paper, we investigate meta-learning approaches for adaptation of the trace decay parameter {\lambda} used in TD({\lambda}), from the perspective of optimizing a bias-variance tradeoff. We propose an off-policy applicable method of meta-learning the {\lambda} parameters via optimizing a metaobjective with effcient incremental updates. The proposed trust-region style algorithm, under proper assumptions, is shown to be equivalent to optimizing the bias-variance tradeoff for the overall target for all states. In experiments, we validate the effectiveness of the proposed method MTA showing its significantly faster and more accurate learning patterns compared to the compared methods and baselines.

Towards a framework for the evolution of artificial general intelligence (1903.10410v3)

Sidney Pontes-Filho, Stefano Nichele

2019-03-25

In this work, a novel framework for the emergence of general intelligence is proposed, where agents evolve through environmental rewards and learn throughout their lifetime without supervision, i.e., self-supervised learning through embodiment. The chosen control mechanism for agents is a biologically plausible neuron model based on spiking neural networks. Network topologies become more complex through evolution, i.e., the topology is not fixed, while the synaptic weights of the networks cannot be inherited, i.e., newborn brains are not trained and have no innate knowledge of the environment. What is subject to the evolutionary process is the network topology, the type of neurons, and the type of learning. This process ensures that controllers that are passed through the generations have the intrinsic ability to learn and adapt during their lifetime in mutable environments. We envision that the described approach may lead to the emergence of the simplest form of artificial general intelligence.

Assistive System in Conversational Agent for Health Coaching: The CoachAI Approach (1904.11412v1)

Ahmed Fadhil

2019-04-25

With increasing physicians' workload and patients' needs for care, there is a need for technology that facilitates physicians work and performs continues follow-up with patients. Existing approaches focus merely on improving patient's condition, and none have considered managing physician's workload. This paper presents an initial evaluation of a conversational agent assisted coaching platform intended to manage physicians' fatigue and provide continuous follow-up to patients. We highlight the approach adapted to build the chatbot dialogue and the coaching platform. We will particularly discuss the activity recommender algorithms used to suggest insights about patients' condition and activities based on previously collected data. The paper makes three contributions: (1) present the conversational agent as an assistive virtual coach, (2) decrease physicians workload and continuous follow up with patients, all by handling some repetitive physician tasks and performing initial follow up with the patient, (3) present the activity recommender that tracks previous activities and patient information and provides useful insights about possible activity and patient match to the coach. Future work focuses on integrating the recommender model with the CoachAI platform and test the prototype with patient's in collaboration with an ambulatory clinic.

---