Recurrent Networks are one of the most powerful and promising artificial neural network algorithms to processing the sequential data such as natural languages, sound, time series data. Unlike traditional feed-forward network, Recurrent Network has a inherent feed back loop that allows to store the temporal context information and pass the state of information to the entire sequences of the events. This helps to achieve the state of art performance in many important tasks such as language modeling, stock market prediction, image captioning, speech recognition, machine translation and object tracking etc., However, training the fully connected RNN and managing the gradient flow are the complicated process. Many studies are carried out to address the mentioned limitation. This article is intent to provide the brief details about recurrent neurons, its variances and trips & tricks to train the fully recurrent neural network. This review work is carried out as a part of our IPO studio software module 'Multiple Object Tracking'.

An automatic program that generates constant profit from the financial market is lucrative for every market practitioner. Recent advance in deep reinforcement learning provides a framework toward end-to-end training of such trading agent. In this paper, we propose an Markov Decision Process (MDP) model suitable for the financial trading task and solve it with the state-of-the-art deep recurrent Q-network (DRQN) algorithm. We propose several modifications to the existing learning algorithm to make it more suitable under the financial trading setting, namely 1. We employ a substantially small replay memory (only a few hundreds in size) compared to ones used in modern deep reinforcement learning algorithms (often millions in size.) 2. We develop an action augmentation technique to mitigate the need for random exploration by providing extra feedback signals for all actions to the agent. This enables us to use greedy policy over the course of learning and shows strong empirical performance compared to more commonly used epsilon-greedy exploration. However, this technique is specific to financial trading under a few market assumptions. 3. We sample a longer sequence for recurrent neural network training. A side product of this mechanism is that we can now train the agent for every T steps. This greatly reduces training time since the overall computation is down by a factor of T. We combine all of the above into a complete online learning algorithm and validate our approach on the spot foreign exchange market.

The key issue of few-shot learning is learning to generalize. In this paper, we propose a large margin principle to improve the generalization capacity of metric based methods for few-shot learning. To realize it, we develop a unified framework to learn a more discriminative metric space by augmenting the softmax classification loss function with a large margin distance loss function for training. Extensive experiments on two state-of-the-art few-shot learning models, graph neural networks and prototypical networks, show that our method can improve the performance of existing models substantially with very little computational overhead, demonstrating the effectiveness of the large margin principle and the potential of our method.

Last month Airbus released a video of the first successful test flight of its electric vertical take-off and landing (eVTOL) autonomous drone. Although it only hovered in the air for 53 seconds, the fact that its eight rotors were powered entirely by electricity was a landmark for the manufacturer of gas-guzzling planes. The goal is that the technology could be used for airborne travel in congested cities. "Our goal is to democratise personal flight by leveraging the latest technologies such as electric propulsion, energy storage and machine vision," blogged Zach Lovering, Vahana project executive. Chinese drone manufacturer Ehang is considerably more advanced than Airbus. In February it flew 40 journalists and local dignitaries on trips of up to 15km in Guangzhou, southern China, reaching top speeds of 80mph.

In a race to dominate the artificial intelligence (AI) space, Microsoft is bringing the power of AI to users and organisations through'Microsoft Cognitive Services (MCS).' MCS is a collection of intelligent APIs (application programming interfaces) that allow systems to see, hear, speak, understand and interpret human needs using natural methods of communication. Products that analyse human emotions, AI technology that describes surroundings to visually-challenged and an Indian chatbot that interacts with users like a friend, were some of the innovations that Microsoft recently showcased at its research lab in Bengaluru. "We don't think about computers as competing with humans or replacing them," said Sriram Rajamani, distinguished scientist and managing director, Microsoft Research India Lab. "We think about them as amplifying human ability," he said.

Shares in the world's largest smartphone and semiconductor maker slid 2.3% on Friday after Samsung said it expected second-quarter operating profits of 14.8 trillion won ($13.2 billion), below analyst estimates of 15.1 trillion won. That result would break the South Korean company's string of four record-shattering quarters. Memory chips go in everything from smartphones to internet-connected light bulbs to self-driving cars, and growth in demand for the chips had outrun supply. The current pullback in their pricing reflects stepped-up production by manufacturers plus sluggish smartphone sales. Even so, the industry is still healthy.

Phil Rosenthal, the host of Netflix's "Somebody Feed Phil," meets Jefferson Graham for lunch, and reveals his top 3 favorite destinations in the world. Phil Rosenthal is the star of Netflix's travel documentary series "Somebody Feed Phil" (Photo: Jefferson Graham) LOS ANGELES -- At age 58, Phil Rosenthal finally has a website, https://www.philrosenthalworld.com The star of Netflix's globe-trotting "Somebody Feed Phil," travel documentary series had a previous life as the co-creator of "Everybody Loves Raymond," and was happy to have people look him on his IMDB page. But now that he's got a second act as an internet video star, with "Phil," he realized he needed more, as his fans were demanding it. "They would sit with a pencil, writing the names of the places we visited as the show was on," says Rosenthal.

Once a year, the bucolic grounds of Goodwood House in West Sussex, England, are consumed by the smell of exhaust fumes, the sound of engines revving, and an excited crowd of 100,000 people, all wanting a look at the special cars on show. They gather here because Charles Gordon-Lennox, the 11th Duke of Richmond, likes to occasionally open his home to host the Goodwood Festival of Speed, a celebration of all the history, the heritage, and the future of motor racing. This week, among the supercars, hypercars, and pure racing cars, Goodwood visitors will spot a low, black machine streaking in near silence up the winding driveway to the estate, which for the event is transformed into a 1.16-mile hill climb track. "We're pretty sure when the car appears, people will freak out," says Rod Chong, deputy CEO of Roborace. And it will be the first machine to give the hill climb a try without a human in command, so there are some nerves.

Life is full of little disappointments. That's why it's so refreshing to occasionally see someone do something grand, and just a bit nutty. Like Elon Musk setting up a fully functional production tent in the Tesla's factory's backyard, in a improbable--and thus far successful!--bid to hit his 2018 production targets. Like a developer taking a polluted ex-Ford factory in Minnesota and trying to turn it into a walker-friendly, net-zero energy planned community. Like the mere existence of the Polaris Slingshot, which is not quite a car and not quite a motorcycle, but tells us some important things about the future of transportation. This week, it was all about lofty goals.

Artificial Intelligence (AI) is fast evolving as the go-to technology for companies across the world to personalise experience for individuals. The technology itself is getting better and smarter day by day, allowing more and newer industries to adopt the AI for various applications. Banking sector is becoming one of the first adopters of AI. And just like other segments, banks are exploring and implementing the technology in various ways. The rudimentary applications AI include bring smarter chat-bots for customer service, personalising services for individuals, and even placing an AI robot for self-service at banks.