Your maps assistant makes sure you reach your destinations at the right time, your autocorrect promptly lets you know whenever you might misspell a word, and apps display neat lists of recommendations drawing from your recent search data… Essentially, from when you enjoy your first cup of tea in the morning till the time your head hits your pillow, wherever you turn, you are likely to see manifestations of the subversive emerging technology of artificial intelligence. In this blog, we will be getting acquainted with 15 of these popular use cases of AI. Need to process speech and audio data input? Speaking of explanatory inference, you would apply inference rules to glean proofs in AI, and the proof is a sequence of the conclusion that leads to the goal. Decoding an image might not always be enough, prediction may come into the picture, so AI software comes in handy!

Good TVs are always in high demand, so finding deals can be a fruitless quest. If you're on the lookout for one, Amazon is running a one-day sale right now on LG, Samsung and Sony sets, including OLED and other desirable models at all-time low prices. For instance, LG's 55-inch A1 OLED is just $797 instead of $1,300 for the biggest savings we've seen yet. Sony's A80J 65-inch OLED model is $1,399 or 44 percent off (a new low), and Samsung's 55-inch Frame TV with Quantum HDR is priced at just $980, also an all-time low. LG's 2021 line of A1 OLED TVs first appeared at CES 2021, offering support for Dolby Vision, Dolby Atmos, Filmmaker mode, Google Assistant, Amazon Alexa and AirPlay 2. You can expect a color accurate picture with deep blacks, though some things are missing like a 120Hz display and HDMI 2.1. Still, at $797, the 55-inch A1 will deliver everything else you might want in an OLED TV.

The tweet landed like a burp on a first date: a little awkward, potentially endearing, maybe a good story to tell later. Chris Olah, a neural network engineer for a company called AnthropicAI and a former Thiel Foundation fellow, observed out loud on Wednesday, "Normal online dating seems pretty suboptimal. Recently, I've seen several people experiment with public'date me' docs--I think this is a really interesting experiment in alternatives, enabling long-form, earnest dating profiles." Olah linked to his own Date Me doc in his tweet. Olah is 29, with the grin and just-finished-hiking complexion of someone even younger. The title of his Google Doc gets right to the point: "Male, Straight, 5'7", Monogamous, Wants Kids."

Machine learning is an application of artificial intelligence in which data is made available to machines so they can learn from it as opposed to having to be trained by humans to think and act in certain ways regarding the data. Every time Alexa or Siri responds incorrectly to your request, they learn from the error and utilize that information to react more accurately the next time. If a mistake was made, it uses that information to make improvements. The system also records if the reaction was favorable. The microphone on the device you are using records your request when you speak to Alexa or Siri.

One of the key challenges of learning an online recommendation model is the temporal domain shift, which causes the mismatch between the training and testing data distribution and hence domain generalization error. To overcome, we propose to learn a meta future gradient generator that forecasts the gradient information of the future data distribution for training so that the recommendation model can be trained as if we were able to look ahead at the future of its deployment. Compared with Batch Update, a widely used paradigm, our theory suggests that the proposed algorithm achieves smaller temporal domain generalization error measured by a gradient variation term in a local regret. We demonstrate the empirical advantage by comparing with various representative baselines.

Sequential recommendation predicts users' next behaviors with their historical interactions. Recommending with longer sequences improves recommendation accuracy and increases the degree of personalization. As sequences get longer, existing works have not yet addressed the following two main challenges. Firstly, modeling long-range intra-sequence dependency is difficult with increasing sequence lengths. Secondly, it requires efficient memory and computational speeds. In this paper, we propose a Sparse Attentive Memory (SAM) network for long sequential user behavior modeling. SAM supports efficient training and real-time inference for user behavior sequences with lengths on the scale of thousands. In SAM, we model the target item as the query and the long sequence as the knowledge database, where the former continuously elicits relevant information from the latter. SAM simultaneously models target-sequence dependencies and long-range intra-sequence dependencies with O(L) complexity and O(1) number of sequential updates, which can only be achieved by the self-attention mechanism with O(L^2) complexity. Extensive empirical results demonstrate that our proposed solution is effective not only in long user behavior modeling but also on short sequences modeling. Implemented on sequences of length 1000, SAM is successfully deployed on one of the largest international E-commerce platforms. This inference time is within 30ms, with a substantial 7.30% click-through rate improvement for the online A/B test. To the best of our knowledge, it is the first end-to-end long user sequence modeling framework that models intra-sequence and target-sequence dependencies with the aforementioned degree of efficiency and successfully deployed on a large-scale real-time industrial recommender system.

In this work we introduce an incremental learning framework for Click-Through-Rate (CTR) prediction and demonstrate its effectiveness for Taboola's massive-scale recommendation service. Our approach enables rapid capture of emerging trends through warm-starting from previously deployed models and fine tuning on "fresh" data only. Past knowledge is maintained via a teacher-student paradigm, where the teacher acts as a distillation technique, mitigating the catastrophic forgetting phenomenon. Our incremental learning framework enables significantly faster training and deployment cycles (x12 speedup). We demonstrate a consistent Revenue Per Mille (RPM) lift over multiple traffic segments and a significant CTR increase on newly introduced items.

Most of your day is probably spent on your phone. From sending emails to watching videos, from searching for work to reading the news, it's almost impossible not to spend time on one of the most important pieces of technology in our world. That's why it was only a matter of time until artificial intelligence came knocking on that door. Though sometimes, as with any new technology, all the possibilities and potential greatness can be somewhat overwhelming. Think of artificial intelligence as technology that can learn, understand, and make decisions and predictions similar to a human.

Contextual multi-armed bandit (MAB) is an important sequential decision-making problem in recommendation systems. A line of works, called the clustering of bandits (CLUB), utilize the collaborative effect over users and dramatically improve the recommendation quality. Owing to the increasing application scale and public concerns about privacy, there is a growing demand to keep user data decentralized and push bandit learning to the local server side. Existing CLUB algorithms, however, are designed under the centralized setting where data are available at a central server. We focus on studying the federated online clustering of bandit (FCLUB) problem, which aims to minimize the total regret while satisfying privacy and communication considerations. We design a new phase-based scheme for cluster detection and a novel asynchronous communication protocol for cooperative bandit learning for this problem. To protect users' privacy, previous differential privacy (DP) definitions are not very suitable, and we propose a new DP notion that acts on the user cluster level. We provide rigorous proofs to show that our algorithm simultaneously achieves (clustered) DP, sublinear communication complexity and sublinear regret. Finally, experimental evaluations show our superior performance compared with benchmark algorithms.

The mission of Just Eat Takeaway is to empower users' every food moment. A big part of fulfilling that mission is ensuring that we show the right restaurants to the right users. To do this, we design large-scale machine learning recommendation systems that can learn which types of users tend to enjoy which types of restaurants. A crucial part of this process is being able to compare the quality of different recommendation systems, in order to decide which is most effective. The gold standard approach to this evaluation problem is A/B testing - allow the different systems to recommend items to randomly selected groups of users, and compare their relative performance. However, A/B testing is both slow, taking time to reach sufficient statistical power, and expensive [5, 1] if we serve poor recommendations to a subset of users. Therefore, evaluating recommender systems in offline fashion without running A/B tests is of significant importance. These offline approaches avoid serving experimental recommenders to users, and instead evaluates them using old online data, where users were served recommendations from a different system. Metrics such as Root Mean Squared Error [2] Mean Average Precision, Normalized Discounted Cumulative Gain, Mean Reciprocal Rank and Hit Rate have been used repeatedly for offline evaluation.