Abstract--convolutional neural networks are the most widely used deep learning algorithms for traffic signal classification till date[1] but they fail to capture pose, view, orientation of the images because of the intrinsic inability of max pooling layer.This paper proposes a novel method for Traffic sign detection using deep learning architecture called capsule networks that achieves outstanding performance on the German traffic sign dataset.Capsule network consists of capsules which are a group of neurons representing the instantiating parameters of an object like the pose and orientation[2] by using the dynamic routing and route by agreement algorithms.unlike the previous approaches of manual feature extraction,multiple deep neural networks with many parameters,our method eliminates the manual effort and provides resistance to the spatial variances.CNNs can be fooled easily using various adversary attacks[3] and capsule networks can overcome such attacks from the intruders and can offer more reliability in traffic sign detection for autonomous vehicles.Capsule network have achieved the state-of-the-art accuracy of 97.6% on German Traffic Sign Recognition Benchmark dataset (GTSRB). I. INTRODUCTION Traffic sign detection is a real world task which involves lot of constraints and complications.Even a minor misclassification of the traffic sign can lead to catastrophic consequences and can even lead to loss of life.It is implemented in various advanced driver assistance systems and in autonomous vehicles.A camera is present on the dashboard of the vehicle and it captures the real time video feed which is sampled into frames and fed to a deep learning model which is deployed inside a automotive embedded board.As the vehicle is driven in various environments,lighting conditions,speeds and geographies it is essential for the deep learning algorithm to be robust and reliable at all times.The camera can capture the traffic sign in different orientations and poses but the algorithm should be able to recognize the correct sign[4] and capsule networks are the perfect deep learning algorithm in addressing this problem. Generally Convolutional neural networks are used for all the state of the art deep learning neural network algorithms[5] in most of the image related tasks.Convolution captures the spatial information of the image using the kernel function in convolution layer. A CNN consists of input, output and hidden layers. The hidden layers further consists of convolutional, pooling, fully connected and normalization layers.

Existing attention mechanisms either attend to local image grid or object level features for Visual Question Answering (VQA). Motivated by the observation that questions can relate to both object instances and their parts, we propose a novel attention mechanism that jointly considers reciprocal relationships between the two levels of visual details. The bottom-up attention thus generated is further coalesced with the top-down information to only focus on the scene elements that are most relevant to a given question. Our design hierarchically fuses multi-modal information i.e., language, object- and gird-level features, through an efficient tensor decomposition scheme. The proposed model improves the state-of-the-art single model performances from 67.9% to 68.2% on VQAv1 and from 65.3% to 67.4% on VQAv2, demonstrating a significant boost.

Extracting action sequences from natural language texts is challenging, as it requires commonsense inferences based on world knowledge. Although there has been work on extracting action scripts, instructions, navigation actions, etc., they require that either the set of candidate actions be provided in advance, or that action descriptions are restricted to a specific form, e.g., description templates. In this paper, we aim to extract action sequences from texts in free natural language, i.e., without any restricted templates, provided the candidate set of actions is unknown. We propose to extract action sequences from texts based on the deep reinforcement learning framework. Specifically, we view "selecting" or "eliminating" words from texts as "actions", and the texts associated with actions as "states". We then build Q-networks to learn the policy of extracting actions and extract plans from the labeled texts. We demonstrate the effectiveness of our approach on several datasets with comparison to state-of-the-art approaches, including online experiments interacting with humans.

We decided to take a closer look at this, and truly double-click on the "high-mileage" experience our customers have had with the NVIDIA DGX-1. To do this, we commissioned Forrester Research to meet with a variety of customers from various industries, all of whom have built their deep learning workflow on NVIDIA, and explore what the day-in, day-out operational experience has been like.

I had a new talk presented at "Codemotion Amsterdam 2018" this week. I discussed the relation of Apache Kafka and Machine Learning to build a Machine Learning infrastructure for extreme scale. As always, I want to share the slide deck. The talk was also recorded. I will share the video as soon as it was published by the organizer.

Deep learning is a sub-category within machine learning and artificial intelligence. It is inspired by and based on the model of the human brain to create artificial neural networks for machines. Deep learning will allow machines and devices to function in some ways as humans do. Dr. Rodrigo Agundez of GoDataDriven is co-author of this article and very enthusiastic about the improvements that deep learning can offer. He's been involved in the data science and analysis field for some time, and is already working on implementing models for practical applications.

Machine learning and artificial intelligence (AI) are all the rage these days -- but with all the buzzwords swirling around them, it's easy to get lost and not see the difference between hype and reality. For example, just because an algorithm is used to calculate information doesn't mean the label "machine learning" or "artificial intelligence" should be applied. Before we can even define AI or machine learning, though, I want to take a step back and define a concept that is at the core of both AI and machine learning: algorithm. An algorithm is a set of rules to be followed when solving problems. In machine learning, algorithms take in data and perform calculations to find an answer.

Booz Allen and NVIDIA are offering deep learning training. NVIDIA is working with Booz Allen Hamilton to rapidly build solutions that are needed in cyberdefense for both government and commercial customers. Now, certified Deep Learning Institute instructors from NVIDIA and Booz Allen are offering training to a variety of customers on how to build your own effective deep learning and data-driven solutions. 'Deep Learning Demystified,' hosted by Booz Allen and NVIDIA, will provide instructor-led and hands-on deep learning training. Introduce yourself to key terminology, use cases from various industries, and learn how to effectively train, optimize, and deploy a neural network.

LONDON, ENGLAND - DECEMBER 05: Co-founder of Google DeepMind Mustafa Suleyman attends a Q&A during day 1 of TechCrunch Disrupt London at the Copper Box on December 5, 2016 in London, England. Google has found another use for DeepMind's machine learning software after buying the London artificial intelligence lab for a reported £400 million in 2014. Later this year, the search giant will roll out two new DeepMind-built Android features that are designed to improve battery life and optimise screen brightness levels. The features will be available to people with devices running the Android P operating system. The features -- announced during the Google I/O developer conference -- were built by a unit called "DeepMind for Google," which focuses on applying DeepMind's technology to Google products.

Google has found another use for DeepMind's machine learning software after buying the London artificial intelligence lab for a reported £400 million in 2014. Later this year, the search giant will roll out two new DeepMind-built Android features that are designed to improve battery life and optimise screen brightness levels. The features will be available to people with devices running the Android P operating system. The features -- announced during the Google I/O developer conference -- were built by a unit called "DeepMind for Google," which focuses on applying DeepMind's technology to Google products. The same unit has also helped Google to reduce energy use in its data centres, optimise recommendations in Google Play, and improve the speech for Google Assistant users and Google Cloud Platform users.