Effective solving of constraint problems often requires choosing good or specific search heuristics. However, choosing or designing a good search heuristic is non-trivial and is often a manual process. In this paper, rather than manually choosing/designing search heuristics, we propose the use of bandit-based learning techniques to automatically select search heuristics. Our approach is online where the solver learns and selects from a set of heuristics during search. The goal is to obtain automatic search heuristics which give robust performance. Preliminary experiments show that our adaptive technique is more robust than the original search heuristics. It can also outperform the original heuristics.

While searching for things over internet, I always wondered, what kind of algorithms might be running behind these search engines which provide us with the most relevant information? How do they decide which result to show for which set of search keywords. This might be a no brainer for a few people, but definitely an interesting problem for some of the best brains around the world. To find the answer, I read every guide, tutorial, learning material that came my way. Information retrieval system is a network of algorithms, which facilitate the search of relevant data / documents as per the user requirement.

Google has introduced new shopping campaigns for AdWords, which utilize automation and machine learning to maximize conversion value. If an advertiser were to define their conversion value as "revenue," for example, then AdWords will automatically optimize the shopping campaign to maximize revenue based on budget constraints. Standard shopping campaigns will continue to be offered along with Google AdWords' new goal-optimized shopping campaigns. Google boasts that the new shopping campaign type "offers a fully-automated solution to drive sales and reach more customers." The new shopping campaigns will be automatically optimized to help marketers achieve their specific goal, whether it's maximizing conversion value or maximizing conversion value at a specific return on ad spend.

We formulate a private learning model to study an intrinsic tradeoff between privacy and query complexity in sequential learning. Our model involves a learner who aims to determine a scalar value, $v^*$, by sequentially querying an external database and receiving binary responses. In the meantime, an adversary observes the learner's queries, though not the responses, and tries to infer from them the value of $v^*$. The objective of the learner is to obtain an accurate estimate of $v^*$ using only a small number of queries, while simultaneously protecting her privacy by making $v^*$ provably difficult to learn for the adversary. Our main results provide tight upper and lower bounds on the learner's query complexity as a function of desired levels of privacy and estimation accuracy. We also construct explicit query strategies whose complexity is optimal up to an additive constant.

Understanding SEO is the first rule for being able to optimize your site and its content so that would-be customers can actually find your company online. When your SEO is on point, you are more likely appear in search engine results when someone looks for the type of products or services you sell. However, to be able to truly understand SEO, you need to comprehend how modern search engines work -- and that means understanding artificial intelligence, or AI. AI is a technological advancement that enables a combination of hardware and software to function like a human brain -- minus the inherent flaws in logic and the relatively small memory capacity. It makes it possible to not only analyze large amounts of data but to draw meaningful insights about the information.

Journal of Parallel and Distributed Computing 104, 19-35.

Chit-chat models are known to have several problems: they lack specificity, do not display a consistent personality and are often not very captivating. In this work we present the task of making chit-chat more engaging by conditioning on profile information. We collect data and train models to (i) condition on their given profile information; and (ii) information about the person they are talking to, resulting in improved dialogues, as measured by next utterance prediction. Since (ii) is initially unknown our model is trained to engage its partner with personal topics, and we show the resulting dialogue can be used to predict profile information about the interlocutors.

Multi-modal data is becoming more common than before because of big data issues. Finding the semantically equal or similar objects from different data sources(called entity resolution) is one of the heart problem of multi-modal task. Current models for solving this problem usually needs much paired data to find the latent correlation between multi-modal data, which is of high cost. A new kind latent correlation is proposed in this article. With the correlation, multi-modal objects can be uniformly represented in a commonly shard space. A classifying based model is designed for multi-modal entity resolution task. With the proposed method, the demand of training data can be decreased much.

Initially developed by Facebook, Presto is an open source, distributed ANSI SQL query engine that delivers fast analytic queries against various data sources ranging in size from gigabytes to petabytes. For data scientists, this is ideal for returning Big Data query results in seconds, accelerating the iterative nature of data science discoveries by powering dashboards, reporting and ad-hoc analysis. Presto was designed and built from scratch to be a fast SQL query engine. It follows the classic MPP SQL engine design in which query processing is parallelized over a cluster of machines. As a result, highly concurrent queries execute at interactive speeds.

We propose a simple, robust, and scalable reverse image search engine that leverages convolutional features from Keras' pre-trained neural networks and the distance metric from Scikit-Learn's K-Nearest Neighbors. We show example queries using data scraped from Google images, and dive deeper in how we use the search engine to track the proliferation of memes from the dark web.