Conventional simulations on multi-exit indoor evacuation focus primarily on how to determine a reasonable exit based on numerous factors in a changing environment. Results commonly include some congested and other under-utilized exits, especially with massive pedestrians. We propose a multi-exit evacuation simulation based on Deep Reinforcement Learning (DRL), referred to as the MultiExit-DRL, which involves in a Deep Neural Network (DNN) framework to facilitate state-to-action mapping. The DNN framework applies Rainbow Deep Q-Network (DQN), a DRL algorithm that integrates several advanced DQN methods, to improve data utilization and algorithm stability, and further divides the action space into eight isometric directions for possible pedestrian choices. We compare MultiExit-DRL with two conventional multi-exit evacuation simulation models in three separate scenarios: 1) varying pedestrian distribution ratios, 2) varying exit width ratios, and 3) varying open schedules for an exit. The results show that MultiExit-DRL presents great learning efficiency while reducing the total number of evacuation frames in all designed experiments. In addition, the integration of DRL allows pedestrians to explore other potential exits and helps determine optimal directions, leading to the high efficiency of exit utilization.

Deep auto-encoders (DAEs) have achieved great success in learning data representations via the powerful representability of neural networks. But most DAEs only focus on the most dominant structures which are able to reconstruct the data from a latent space and neglect rich latent structural information. In this work, we propose a new representation learning method that explicitly models and leverages sample relations, which in turn is used as supervision to guide the representation learning. Different from previous work, our framework well preserves the relations between samples. Since the prediction of pairwise relations themselves is a fundamental problem, our model adaptively learns them from data. This provides much flexibility to encode real data manifold. The important role of relation and representation learning is evaluated on the clustering task. Extensive experiments on benchmark data sets demonstrate the superiority of our approach. By seeking to embed samples into subspace, we further show that our method can address the large-scale and out-of-sample problem.

Normalising flows are tractable probabilistic models that leverage the power of deep learning to describe a wide parametric family of distributions, all while remaining trainable using maximum likelihood. We discuss how these methods can be further improved based on insights from robust (in particular, resistant) statistics. Specifically, we propose to endow flow-based models with fat-tailed latent distributions such as multivariate Student's $t$, as a simple drop-in replacement for the Gaussian distribution used by conventional normalising flows. While robustness brings many advantages, this paper explores two of them: 1) We describe how using fatter-tailed base distributions can give benefits similar to gradient clipping, but without compromising the asymptotic consistency of the method. 2) We also discuss how robust ideas lead to models with reduced generalisation gap and improved held-out data likelihood. Experiments on several different datasets confirm the efficacy of the proposed approach in both regards.

We introduce an approach for understanding finite-state machine (FSM) representations of recurrent policy networks. Recent work focused on minimizing FSMs to gain high-level insight, however, minimization can obscure a deeper understanding by merging states that are semantically distinct. Conversely, our approach starts with an unminimized machine and applies more-interpretable reductions that preserve the key decision points of the policy. We also contribute a saliency tool to attain a deeper understanding of the role of observations in the decisions. Our case studies on policies from 7 Atari games and 3 control benchmarks demonstrate that the approach can reveal insights that have not been noticed in prior work.

Deep Learning methods are replacing traditional software methods in solving real-world problems. Cheap and easily available computational power combined with labeled big datasets enabled deep learning algorithms to show their full potential. AlexNet paper(2012; Krizhevsky et al.[9]) showed feeding sufficient data into deep neural networks successfully learned to extract representations better than handcrafted features which let the start an era known as the rise of Deep Learning. Their great success in solving otherwise hard engineering problems such as object detection, voice recognition, chatbots, robotic manipulation and autonomous systems shown they can be applied to various fields thanks to their generalisation capability.[16] Path Planning(Motion Planning) is defined as computing a continuous path from starting position S to destination position D while avoiding any known obstacles in the way.[20] Whether it is in 2D or 3D geometry, any robotic system then will able to follow the computed path to reach it's destination. Real World robotic systems tend to use more explainable and reproducible algorithms based on interval based search (A star or Dijkstra) or sampling-based algorithms. We wanted to show a reward based algorithm that depends on Markov Decision Process(MDP) by trying to maximize cumulative future rewards can also complete long term path planning tasks. Advantage of using this option will allow autonomous robot(in our case simulated quadrotor) to create paths in non holonomic constraints which is something current methods fails to achieve.[1][17]

Graphs are networks of dots and lines. Graphs are data structures that can be ingested by various algorithms, notably neural nets, learning to perform tasks such as classification, clustering and regression. TL;DR: here's one way to make graph data ingestable for the algorithms: The result will be vector representation of each node in the graph with some information preserved. Once you have the real number vector, you can feed it to the neural network. The simplest definition of a graph is "a collection of items connected by edges."

The context: One of the greatest unsolved flaws of deep learning is its vulnerability to so-called adversarial attacks. When added to the input of an AI system, these perturbations, seemingly random or undetectable to the human eye, can make things go completely awry. Stickers strategically placed on a stop sign, for example, can trick a self-driving car into seeing a speed limit sign for 45 miles per hour, while stickers on a road can confuse a Tesla into veering into the wrong lane. Safety critical: Most adversarial research focuses on image recognition systems, but deep-learning-based image reconstruction systems are vulnerable too. This is particularly troubling in health care, where the latter are often used to reconstruct medical images like CT or MRI scans from x-ray data.

This article covers some of the most popular books on Data Science and is to assist newcomers in exploring the world of data science and experienced practitioners to get deeper knowledge. Below is a list of the top 8 that I have found useful or been recommended. The following books will give you knowledge and understanding of important areas of data science such as Statistics, Data Science, Machine Learning, Deep Learning and Deployment. This book is very beginner-friendly, easy to read, with a lot of illustrations and real-world scenarios which it combines for an easy to comprehend machine-learning lesson. The strength of the book lies in explaining key concepts.

We all love sport and in our life one time we all wish to get the professional training from the coaches. For everyone it is not possible to afford such fees of the coaches. So we have come with the idea as follows. In every sport the main focus is on angles of the athlete what should be the angle between the hands and legs while doing particular activity. So how it will be if we can detect the angles from the video or photo while doing the particular activity and that angles we can send to the coaches and they can guide the athlete about their mistake and it will help them to improve.

China announced in 2017 its ambition to become the world leader in artificial intelligence (AI) by 2030. While the US still leads in absolute terms, China appears to be making more rapid progress than either the US or the EU, and central and local government spending on AI in China is estimated to be in the tens of billions of dollars.