Belief Propagation (BP) is an important message-passing algorithm for various reasoning tasks over graphical models, including solving the Constraint Optimization Problems (COPs). It has been shown that BP can achieve state-of-the-art performance on various benchmarks by mixing old and new messages before sending the new one, i.e., damping. However, existing methods on tuning a static damping factor for BP not only is laborious but also harms their performance. Moreover, existing BP algorithms treat each variable node's neighbors equally when composing a new message, which also limits their exploration ability. To address these issues, we seamlessly integrate BP, Gated Recurrent Units (GRUs), and Graph Attention Networks (GATs) within the massage-passing framework to reason about dynamic weights and damping factors for composing new BP messages. Our model, Deep Attentive Belief Propagation (DABP), takes the factor graph and the BP messages in each iteration as the input and infers the optimal weights and damping factors through GRUs and GATs, followed by a multi-head attention layer.

Mind maps are powerful tools for brainstorming, problem-solving, organizing thoughts, and keeping track of information. There is also a wide variety of ways of constructing a mind map, which makes it valuable to seek feedback and ideas from other people. Nowadays, artificial intelligence can come in handy as a useful tool to generate new ideas and take your imagination in unexpected directions. In this tutorial, I will show you how to create an app that can generate mind maps using the new ChatGPT API in Python and then visualize them in the form of graphs with the framework Streamlit. Before we begin, let's have a look at the final result: If you find any bugs or ideas for improvements, feel free to share them.

Belief Propagation (BP) is an important message-passing algorithm for various reasoning tasks over graphical models, including solving the Constraint Optimization Problems (COPs). It has been shown that BP can achieve state-of-the-art performance on various benchmarks by mixing old and new messages before sending the new one, i.e., damping. However, existing methods of tuning a static damping factor for BP not only are laborious but also harm their performance. Moreover, existing BP algorithms treat each variable node's neighbors equally when composing a new message, which also limits their exploration ability. To address these issues, we seamlessly integrate BP, Gated Recurrent Units (GRUs), and Graph Attention Networks (GATs) within the message-passing framework to reason about dynamic weights and damping factors for composing new BP messages. Our model, Deep Attentive Belief Propagation (DABP), takes the factor graph and the BP messages in each iteration as the input and infers the optimal weights and damping factors through GRUs and GATs, followed by a multi-head attention layer. Furthermore, unlike existing neural-based BP variants, we propose a novel self-supervised learning algorithm for DABP with a smoothed solution cost, which does not require expensive training labels and also avoids the common out-of-distribution issue through efficient online learning. Extensive experiments show that our model significantly outperforms state-of-the-art baselines.

More of the creative work these days is not being done by humans at all. When Dixons Carphone wanted to push shoppers towards its Black Friday sale, the company turned to Artificial Intelligence (AI) software and got the winning line "The time is now". Saul Lopes, head of customer marketing at Dixons Carphone, thinks it worked because it didn't have the words Black Friday in it. His human copywriters had produced dozens of potentially successful sentences but they all mentioned Black Friday. It was technology that broke this chain of thought.

What springs to mind when you think of advertising? Or perhaps trendy people swapping catch phrases in a converted warehouse?' Well, more of the creative work these days is not being done by humans at all. When Dixons Carphone wanted to push shoppers towards its Black Friday sale, the company turned to Artificial Intelligence (AI) software and got the winning line "The time is now". Saul Lopes, head of customer marketing at Dixons Carphone, thinks it worked because it didn't have the words Black Friday in it.

The next time you load up the latest "Call of Duty" video game, you will likely notice a new message from its developers: Black Lives Matter. Infinity Ward, the development studio that makes "Call of Duty," added a message on screen that appears right before the game starts condemning racism and social injustice. "Our community is hurting," reads a portion the message. "The systemic inequalities our community experiences are once again center stage. Call of Duty and Infinity Ward stand for equality and inclusion. We stand against the racism and injustice our Black community endures. Until change happens and Black Lives Matter, we will never truly be the community we strive to be." "Call of Duty," published by Activision, is the latest example of companies and brands using their platforms to speak out on social issues.

Do you thrive on Outlook email, but wish you didn't have to stare at your PC or phone to catch new messages? You don't have to... if you have the right devices. Microsoft's Cortana assistant now lets you check for new Outlook emails using your voice if you're using Windows 10 or a Harman Kardon Invoke speaker and have set your language to US English. If you've used similar features with voice assistants like Siri, it behaves in a similar way: you can ask if there are new messages, get a summary of what's new and (most importantly) offer a short reply if it makes sense.

Today, WhatsApp introduced a new app update that adds compatibility with Carplay. The additional functionality was first noted on the Dutch site iCulture, and it's automatically available who those who update to version 2.18.20 of the app. WhatsApp users who have a vehicle that is CarPlay enabled can now see unread messages, ask Siri to read them messages and use the voice assistant to send new messages. Users will also receive notifications of new messages with the name of the sender. The ability to scroll through a list of messages is not available, however.

In this paper, we study the problem of online optimization of piecewise constant functions. This is motivated by the question of selecting optimal parameters for learning algorithms. Recently, Gupta and Roughgarden (2016) introduced a probably approximately correct (PAC) framework for choosing parameters of algorithms. Imagine a situation, when a website wishes to provide personalized results to a user. To respond to a user's query, the service provider may need to implement a learning (or some other type of) algorithm which involves choosing parameters. The choice of parameters affects the quality of solution and ideally we would like to design a mechanism where the service provider learns from past instances, or at least employs a strategy that has low regret with respect to the single optimal solution in hindsight. In many learning problems, the goal is to find parameters by optimizing a continuous function (of the parameters); however, ever so often one encounters problems with discrete solutions, such as k-means or independent set, which result in objective functions that have discontinuities. Concretely, we consider the problem of online optimization of piecewise constant functions over the domain [0, 1).