Deep learning approaches have shown promising results in solving routing problems. However, there is still a substantial gap in solution quality between machine learning and operations research algorithms. Recently, another line of research has been introduced that fuses the strengths of machine learning and operational research algorithms. In particular, search perturbation operators have been used to improve the solution. Nevertheless, using the perturbation may not guarantee a quality solution. This paper presents "Learning to Guide Local Search" (L2GLS), a learning-based approach for routing problems that uses a penalty term and reinforcement learning to adaptively adjust search efforts. L2GLS combines local search (LS) operators' strengths with penalty terms to escape local optimals. Routing problems have many practical applications, often presetting larger instances that are still challenging for many existing algorithms introduced in the learning to optimise field. We show that L2GLS achieves the new state-of-the-art results on larger TSP and CVRP over other machine learning methods.

In this paper, human semen samples from the visem dataset collected by the Simula Research Laboratory are automatically assessed with machine learning methods for their quality in respect to sperm motility. Several regression models are trained to automatically predict the percentage (0 to 100) of progressive, non-progressive, and immotile spermatozoa in a given sample. The video samples are adopted for three different feature extraction methods, in particular custom movement statistics, displacement features, and motility specific statistics have been utilised. Furthermore, four machine learning models, including linear Support Vector Regressor (SVR), Multilayer Perceptron (MLP), Convolutional Neural Network (CNN), and Recurrent Neural Network (RNN), have been trained on the extracted features for the task of automatic motility prediction. Best results for predicting motility are achieved by using the Crocker-Grier algorithm to track sperm cells in an unsupervised way and extracting individual mean squared displacement features for each detected track. These features are then aggregated into a histogram representation applying a Bag-of-Words approach. Finally, a linear SVR is trained on this feature representation. Compared to the best submission of the Medico Multimedia for Medicine challenge, which used the same dataset and splits, the Mean Absolute Error (MAE) could be reduced from 8.83 to 7.31. For the sake of reproducibility, we provide the source code for our experiments on GitHub.

Face parsing infers a pixel-wise label to each facial component, which has drawn much attention recently. Previous methods have shown their success in face parsing, which however overlook the correlation among facial components. As a matter of fact, the component-wise relationship is a critical clue in discriminating ambiguous pixels in facial area. To address this issue, we propose adaptive graph representation learning and reasoning over facial components, aiming to learn representative vertices that describe each component, exploit the component-wise relationship and thereby produce accurate parsing results against ambiguity. In particular, we devise an adaptive and differentiable graph abstraction method to represent the components on a graph via pixel-to-vertex projection under the initial condition of a predicted parsing map, where pixel features within a certain facial region are aggregated onto a vertex. Further, we explicitly incorporate the image edge as a prior in the model, which helps to discriminate edge and non-edge pixels during the projection, thus leading to refined parsing results along the edges. Then, our model learns and reasons over the relations among components by propagating information across vertices on the graph. Finally, the refined vertex features are projected back to pixel grids for the prediction of the final parsing map. To train our model, we propose a discriminative loss to penalize small distances between vertices in the feature space, which leads to distinct vertices with strong semantics. Experimental results show the superior performance of the proposed model on multiple face parsing datasets, along with the validation on the human parsing task to demonstrate the generalizability of our model.

It is not a surprise that in the world of Big Data, where the use of deep neural networks (NNs) is common, processing power is essential. GPU is essential for deep learning as it can handle many small processes at the same time, which is needed to update all the weights and bias terms in the layers of deep NN. As deep NN trains, it needs to calculate, re-calculate, adjust, re-scale, and update all of the parameters in every layer of the network thousands, millions, or even billions of times. Doing all of these using CPU would lead to significant time delays. Simply, imagine updating thousand of parameters one after another.

All human beings--even famous movie directors like Federico Fellini--have a finite lifespan. But can their talent live on (and continue to create) with artificial intelligence? Campari Red Diaries: Fellini ForwardCampari Red Diaries: Fellini Forward, a short film and behind-the-scenes documentary, premieres at the Venice Film Festival on Sept. 7, and will be featured at the New York Film Festival before an on-demand release in select markets. While there are three humans with directorial credits--Zackary Canepari and Drea Cooper for the documentary, and Maximilian Niemann on the short film--the post-human creative force on this movie is AI, masterminded by innovation production studio UNIT9. We spoke with Marc D'Souza, Production Director at UNIT9, to find out more. The question behind Campari Red Diaries: Fellini Forward is whether AI can be trained to not just imitate Fellini's oeuvre, but extend it into new and original work.

Computer scientists have created an AI called BAYOU that is able to write its own software code, Though there have been attempts in the past at creating software that can write its own code, programmers generally needed to write as much or more code to tell the program what kind of applications they want it to code as they would write if they just coded the app itself. The AI studies all the code posted on GitHub and uses that to write its own code. Using a process called neural sketch learning, the AI reads all the code and then associates an "intent" behind each. Now when a human asks BAYOU to create an app, BAYOU associates the intent it learned from codes on Github to the user's request and begins writing the app it thinks the user wants. As reported by Futurism, BAYOU is a deep learning tool that basically works like a search engine for coding: tell it what sort of program you want to create with a couple of keywords, and it will spit out java code that will do what you're looking for, based on its best guess.

The graph represents a network of 1,251 Twitter users whose tweets in the requested range contained "#iiot", or who were replied to or mentioned in those tweets. The network was obtained from the NodeXL Graph Server on Tuesday, 14 September 2021 at 21:00 UTC. The requested start date was Tuesday, 14 September 2021 at 00:01 UTC and the maximum number of tweets (going backward in time) was 7,500. The tweets in the network were tweeted over the 1-day, 16-hour, 41-minute period from Sunday, 12 September 2021 at 07:20 UTC to Tuesday, 14 September 2021 at 00:01 UTC. Additional tweets that were mentioned in this data set were also collected from prior time periods.

Edge AI chip startup Deep Vision has raised $35 million in a series B round of funding led by Tiger Global, joined by existing investors Exfinity Venture Partners, Silicon Motion and Western Digital. The company began shipping its first-generation chip last year. ARA-1 is designed for power-efficient, low-latency edge AI processing in applications like smart retail, smart city and robotics. While the company's name suggests a focus on convolutional neural networks, ARA-1 can also accelerate natural language processing with support for complex networks such as long short-term memory (LSTMs) and recurrent neural networks (RNNs). A second-generation chip, ARA-2 with additional features for accelerating LSTMs and RNNs will launch next year.

Deep Learning for NLP - Part 9 Natural language processing (NLP) is a crucial part of artificial intelligence (AI), modeling how people share information. Description Since the proliferation of social media usage, hate speech has become a major crisis. On the one hand, hateful content creates an unsafe environment for certain members of our society. On the other hand, in-person moderation of hate speech causes distress to content moderators. Additionally, it is not just the presence of hate speech in isolation but its ability to dissipate quickly, where early detection and intervention can be most effective.

CLIP is a gigantic leap forward, bringing many of the recent developments from the realm of natural language processing into the mainstream of computer vision: unsupervised learning, transformers, and multimodality to name a few. The burst of innovation it has inspired shows its versatility. And this is likely just the beginning. There has been scuttlebutt recently about the coming age of "foundation models" in artificial intelligence that will underpin the state of the art across many different problems in AI; I think CLIP is going to turn out to be the bedrock model for computer vision. In this post, we aim to catalog the continually expanding use-cases for CLIP; we will update it periodically.