3-D printing organs-

In sequential recommender system applications, it is important to develop models that can capture users' evolving interest over time to successfully recommend future items that they are likely to interact with. For users with long histories, typical models based on recurrent neural networks tend to forget important items in the distant past. Recent works have shown that storing a small sketch of past items can improve sequential recommendation tasks. However, these works all rely on static sketching policies, i.e., heuristics to select items to keep in the sketch, which are not necessarily optimal and cannot improve over time with more training data. In this paper, we propose a differentiable policy for sketching (DiPS), a framework that learns a data-driven sketching policy in an end-to-end manner together with the recommender system model to explicitly maximize recommendation quality in the future. We also propose an approximate estimator of the gradient for optimizing the sketching algorithm parameters that is computationally efficient. We verify the effectiveness of DiPS on real-world datasets under various practical settings and show that it requires up to $50\%$ fewer sketch items to reach the same predictive quality than existing sketching policies.

I am regularly asked to summarize my many posts. I thought it would be a good idea to publish on this blog, every Monday, some of the most relevant articles that I have already shared with you on my social networks. Today I will share some of the most relevant articles about Artificial Intelligence and in what form you can find it in today's life. I will also comment on the articles. Artificial Intelligence Is All the Rage.

These tools often allow teams to pre-program questions to gather information (such as "What is your name?"), as well as branching decision trees to help direct users to the proper channels ("Is it a problem with your phone or computer?"). While a pre-programmed chatbot may display an error message if a user inputs an unknown command, a bot that utilizes NLP can be "trained" over the course of multiple interactions to understand context and respond with more organic answers. Over time, these bots can learn to have almost human-like conversations as they direct chatters to the information they're looking for -- and as technology continues to improve, their response capabilities are growing more and more sophisticated. Even for large-scale teams with dozens or hundreds of agents, AI can help handle those first few steps of gathering basic information from users before routing them to a human being who can take care of their problem. These tools often allow teams to pre-program questions to gather information (such as "What is your name?"), as well as branching decision trees to help direct users to the proper channels ("Is it a problem with your phone or computer?").

The development of Artificial Intelligence technology was thought to be rapid, of course. But in the last few years, there has been an exponential increase in the number of platforms, applications, and tools based on machine learning and artificial intelligence technologies. Scientists and developers continue to design and develop intelligent machines that can mimic reasoning, develop and learn knowledge, and attempt to mimic how humans think. Of course, it is really difficult to follow technologies that are developing so fast. For this reason, in order to keep up with these technological developments, we tried to gather Top 10 Artificial Intelligence Technology trends for you.

Cold-start problem is a fundamental challenge for recommendation tasks. The recent self-supervised learning (SSL) on Graph Neural Networks (GNNs) model, PT-GNN, pre-trains the GNN model to reconstruct the cold-start embeddings and has shown great potential for cold-start recommendation. However, due to the over-smoothing problem, PT-GNN can only capture up to 3-order relation, which can not provide much useful auxiliary information to depict the target cold-start user or item. Besides, the embedding reconstruction task only considers the intra-correlations within the subgraph of users and items, while ignoring the inter-correlations across different subgraphs. To solve the above challenges, we propose a multi-strategy based pre-training method for cold-start recommendation (MPT), which extends PT-GNN from the perspective of model architecture and pretext tasks to improve the cold-start recommendation performance. Specifically, in terms of the model architecture, in addition to the short-range dependencies of users and items captured by the GNN encoder, we introduce a Transformer encoder to capture long-range dependencies. In terms of the pretext task, in addition to considering the intra-correlations of users and items by the embedding reconstruction task, we add embedding contrastive learning task to capture inter-correlations of users and items. We train the GNN and Transformer encoders on these pretext tasks under the meta-learning setting to simulate the real cold-start scenario, making the model easily and rapidly being adapted to new cold-start users and items. Experiments on three public recommendation datasets show the superiority of the proposed MPT model against the vanilla GNN models, the pre-training GNN model on user/item embedding inference and the recommendation task.

We study the problem of recommending items to occasional groups (a.k.a. cold-start groups), where the occasional groups are formed ad-hoc and have few or no historical interacted items. Due to the extreme sparsity issue of the occasional groups' interactions with items, it is difficult to learn high-quality embeddings for these occasional groups. Despite the recent advances on Graph Neural Networks (GNNs) incorporate high-order collaborative signals to alleviate the problem, the high-order cold-start neighbors are not explicitly considered during the graph convolution in GNNs. This paper proposes a self-supervised graph learning paradigm, which jointly trains the backbone GNN model to reconstruct the group/user/item embeddings under the meta-learning setting, such that it can directly improve the embedding quality and can be easily adapted to the new occasional groups. To further reduce the impact from the cold-start neighbors, we incorporate a self-attention-based meta aggregator to enhance the aggregation ability of each graph convolution step. Besides, we add a contrastive learning (CL) adapter to explicitly consider the correlations between the group and non-group members. Experimental results on three public recommendation datasets show the superiority of our proposed model against the state-of-the-art group recommendation methods.

Alexa, Amazon's digital assistant, can now listen out for running water and beeping home appliances, the firm has revealed. The tech giant has added both'sound detectors' to Alexa Routines – sequences of tasks linked to Alexa that users can program as a shortcut. It means Alexa can recognise the individual sounds and send a notification to the user via their device so they can attend to them. If users want Alexa to detect the ping of a tumble dryer when it finishes a spin, for example, they can set up a routine for Alexa to send an alert. Alexa, Amazon's digital assistant, can now listen out for running water and beeping appliances, the firm has revealed.

Black Friday and Cyber Monday may have come and gone, but there are still some decent tech sales available right now. Apple's latest AirPods remain discounted to $150, while a number of our other favorite headphones and earbuds remain at record-low prices. A few Roombas are hundreds of dollars less than usual right now and you can still get some laptops, SSDs, smart speakers and more at very affordable prices. Here are the best Cyber Monday tech deals that you can still get today. Apple's latest AirPods are down to $150 at Amazon.

One in four home interactions with Amazon's Alexa are already initiated by Alexa—not humans.