Multi-vehicle routing problem with soft time windows (MVRPSTW) is an indispensable constituent in urban logistics distribution system. In the last decade, numerous methods for MVRPSTW have sprung up, but most of them are based on heuristic rules which require huge computation time. With the rapid increasing of logistics demand, traditional methods incur the dilemma of computation efficiency. To efficiently solve the problem, we propose a novel reinforcement learning algorithm named Multi-Agent Attention Model in this paper. Specifically, the vehicle routing problem is regarded as a vehicle tour generation process, and an encoder-decoder framework with attention layers is proposed to generate tours of multiple vehicles iteratively. Furthermore, a multi-agent reinforcement learning method with an unsupervised auxiliary network is developed for model training. By evaluated on three synthetic networks with different scale, the results demonstrate that the proposed method consistently outperforms traditional methods with little computation time. In addition, we validate the extensibility of the well-trained model by varying the number of customers and capacity of vehicles. Finally, the impact of parameters settings on the algorithmic performance are investigated.

Deep Learning (DL) techniques for Natural Language Processing have been evolving remarkably fast. Recently, the DL advances in language modeling, machine translation and paragraph understanding are so prominent that the potential of DL in Software Engineering cannot be overlooked, especially in the field of program learning. To facilitate further research and applications of DL in this field, we provide a comprehensive review to categorize and investigate existing DL methods for source code modeling and generation. To address the limitations of the traditional source code models, we formulate common program learning tasks under an encoder-decoder framework. After that, we introduce recent DL mechanisms suitable to solve such problems. Then, we present the state-of-the-art practices and discuss their challenges with some recommendations for practitioners and researchers as well.

It seems like every day, another animal is at risk due to climate change. Antarctica's emperor penguin population is the latest to be in trouble. Their numbers have been dwindling thanks to breeding difficulties which are most likely caused by changing temperatures. According to a 2019 study by the British Antarctic Survey, the emperor penguins could completely disappear by 2100. To help save these beautiful creatures, scientists are turning to AI.

IMAGE: The theoretical beam is the goal scientists wished to achieve. As machine learning continues to surpass human performance in a growing number of tasks, scientists at Skoltech have applied deep learning to reconstruct quantum properties of optical systems. Through a collaboration between the quantum optics research laboratories at Moscow State University, led by Sergey Kulik, and members of Skoltech's Deep Quantum Laboratory of CPQM, led by Jacob Biamonte, the scientists have successfully applied machine learning to the state reconstruction problem. Their findings have been reported in the Nature Partner Journal, npj Quantum Information, and are the first to show that machine learning can reconstruct quantum states from experimental data in the presence of noise and detector errors. Skoltech PhD student Adriano Macarone Palmieri, lead author of the study, described the findings as " a new open door towards deeper insights ." Adriano has a Master's Degree in Physics from Bologna and joined Skoltech from Italy, where he worked as a data scientist.

There are 2 types of errors: reducible and irreducible. Irreducible errors arise due to a lack of data. For example, not only the genre, duration, actors but also the mood of the person and the atmosphere while watching the film affects the rating. But we can't predict the mood of the person in the future. The other reason is the quality of the data.

Many application domains increasingly require AD, when anomalies carry critical and actionable information. We shall address the problem of detecting and predicting general anomalies in high-dimension KPI performance metrics, i.e., high dimension and dynamic range multivariate non-stationary time series collected from large Cloud / IT environments. Using Keras / TF etc., we will build an ML-based AD framework for transfer, attention and meta-learning that must remain robust also with reduced/missing and noisy training data. Besides feature engineering -- e.g., selection, reduction, compression techniques -- explainability will also be necessary for the model prototype. The research is to be performed at IBM Research – Zurich Lab, Switzerland.

One application that has really caught the attention of many folks in the space of artificial intelligence is image captioning. If you think about it, there is seemingly no way to tell a bunch of numbers to come up with a caption for an image that accurately describes it. Now, with the power of deep learning, we can achieve this more accurately than we ever imagined. The problem of writing captions for an image is two-fold: you need to get meaning out of the image by extracting relevant features, and you need to translate these features into a human-readable format. In this tutorial, we're going to look at both phases independently and then connect the pieces together.

Keras metrics are functions that are used to evaluate the performance of your deep learning model. Choosing a good metric for your problem is usually a difficult task. Lucky for you, this article explains all that! In Keras, metrics are passed during the compile stage as shown below. You can pass several metrics by comma separating them.

Welcome to Machine Learning Up-To-Date (ML UTD) 1! The LifeWithData blog separates the signal from the noise in today's hectic front lines of software engineering and machine learning. LifeWithData aims to consistently deliver curated machine learning newsletters that point the reader to key developments without massive amounts of backstory for each. This enables frequent, concise updates across the industry without overloading readers with information. ML UTD 1 brings innovations in the fields of edge computing, deep learning, ML standardization. Let's continue moving away from bulky cloud server costs with Pytorch mobile and SwiftUI.

Deepfakes are synthetic media, usually videos, created with deep learning technology. By manipulating images, videos, and voices of real people, a deepfake can portray someone doing things they never did, or saying things they never said. By feeding a machine learning model thousands of target images, a deepfake algorithm can learn the details of a person's face. With enough training data, the algorithm can then predict what that person's face would look like when mimicking the expressions of someone else. A similar process is used for training deepfake algorithms to mimic the accent, intonation, and tone of a person's voice.