You probably already know about artificial intelligence (AI) and how it's being used more and more in our everyday lives. From the recommendation algorithms used by Netflix to the self-driving cars being developed by Tesla, AI is slowly but surely becoming a part of our world. But what you might not know is that there are many limitations in the current process of developing AI technology. Most AI systems are "dumb" in the sense that they can only be trained to do one specific task. For example, there might be a different algorithm for recognizing faces, another for understanding language, and yet another for driving a car.

Machine learning (a subfield of AI) aims to program computers to learn and grow as people do. Machine learning may automate virtually any activity that can be solved using a pattern or set of data-developed rules. It's crucial to have a firm grasp of the various data kinds to clean and preprocess the data in preparation for use with ML algorithms. For machines to recognize patterns in data, it must first be translated into a numerical representation. This will allow us to pick the top-performing models that can quickly and accurately identify the underlying patterns.

Media news are making a large part of public opinion and, therefore, must not be fake. News on web sites, blogs, and social media must be analyzed before being published. In this paper, we present linguistic characteristics of media news items to differentiate between fake news and real news using machine learning algorithms. Neural fake news generation, headlines created by machines, semantic incongruities in text and image captions generated by machine are other types of fake news problems. These problems use neural networks which mainly control distributional features rather than evidence. We propose applying correlation between features set and class, and correlation among the features to compute correlation attribute evaluation metric and covariance metric to compute variance of attributes over the news items. Features unique, negative, positive, and cardinal numbers with high values on the metrics are observed to provide a high area under the curve (AUC) and F1-score.

Recent works on fake news detection have shown the efficacy of using emotions as a feature for improved performance. However, the cross-domain impact of emotion-guided features for fake news detection still remains an open problem. In this work, we propose an emotion-guided, domain-adaptive, multi-task approach for cross-domain fake news detection, proving the efficacy of emotion-guided models in cross-domain settings for various datasets.

Generative adversarial nets (GANs) have been remarkably successful at learning to sample from distributions specified by a given dataset, particularly if the given dataset is reasonably large compared to its dimensionality. However, given limited data, classical GANs have struggled, and strategies like output-regularization, data-augmentation, use of pre-trained models and pruning have been shown to lead to improvements. Notably, the applicability of these strategies is 1) often constrained to particular settings, e.g., availability of a pretrained GAN; or 2) increases training time, e.g., when using pruning. In contrast, we propose a Discriminator gradIent Gap regularized GAN (DigGAN) formulation which can be added to any existing GAN. DigGAN augments existing GANs by encouraging to narrow the gap between the norm of the gradient of a discriminator's prediction w.r.t.\ real images and w.r.t.\ the generated samples. We observe this formulation to avoid bad attractors within the GAN loss landscape, and we find DigGAN to significantly improve the results of GAN training when limited data is available. Code is available at \url{https://github.com/AilsaF/DigGAN}.

Word feature vectors have been proven to improve many NLP tasks. With recent advances in unsupervised learning of these feature vectors, it became possible to train it with much more data, which also resulted in better quality of learned features. Since it learns joint probability of latent features of words, it has the advantage that we can train it without any prior knowledge about the goal task we want to solve. We aim to evaluate the universal applicability property of feature vectors, which has been already proven to hold for many standard NLP tasks like part-of-speech tagging or syntactic parsing. In our case, we want to understand the topical focus of text documents and design an efficient representation suitable for discriminating different topics. The discriminativeness can be evaluated adequately on text categorisation task. We propose a novel method to extract discriminative keywords from documents. We utilise word feature vectors to understand the relations between words better and also understand the latent topics which are discussed in the text and not mentioned directly but inferred logically. We also present a simple way to calculate document feature vectors out of extracted discriminative words. We evaluate our method on the four most popular datasets for text categorisation. We show how different discriminative metrics influence the overall results. We demonstrate the effectiveness of our approach by achieving state-of-the-art results on text categorisation task using just a small number of extracted keywords. We prove that word feature vectors can substantially improve the topical inference of documents' meaning. We conclude that distributed representation of words can be used to build higher levels of abstraction as we demonstrate and build feature vectors of documents.

The giant TVs and high-end laptops might get the lion's share of attention on Black Friday, but the smaller tech devices are worth checking out too. We put the cap at $50 and came up with over 20 deals on inexpensive gadgets along with a few peripherals and accessories you'll need for this year's higher-end buys. Some gadgets are going for all-time lows, like the new Echo Dot. Others, like the Google Nest Mini and the Roku Streaming Stick 4K are half off their usual price. We added a few storage cards that are seeing big price cuts too, since you can never have too many of those.

Now that Amazon has not one but two Prime Days per year, you might think they'd run out of deals. The world's largest retailer has plenty of deals to go around for Black Friday, including these discounts on their own devices. And for this sale, you don't even have to be a Prime member to snag the savings. Amazon makes a slew of its own hardware, including Echo smart speakers, Fire tablets and Kindles. Most come with the ever-improving and evolving smart AI assistant Alexa, giving you the option of unifying your smart home and controlling it just by talking. Lots of these deals match or even beat Prime Day prices, so it's a great time to buy if you want to give the gift of a Kindle or ring in the new year with an Alexa-enabled Echo Show display.

Amazon is having an internal crisis over Alexa right now--its voice assistant is on pace to lose $10 billion this year--so it might not be the best idea to invest in the company's lineup of Alexa-powered devices right now. However, Amazon makes a ton of other hardware, from Kindles, which are some of the best ebook readers in the market, to Fire tablets and Fire TV sticks. Everything is heavily discounted right now during Amazon's Black Friday sale, so now's the best time to buy. We test products year-round and handpicked these deals. Products that are sold out or no longer discounted as of publishing will be crossed out . We'll update this guide throughout the Black Friday and Cyber Monday weekend.

Manipulated images are a threat to consumers worldwide, when they are used to spread disinformation. Therefore, Comprint enables forgery detection by utilizing JPEG-compression fingerprints. This paper evaluates the impact of the training set on Comprint's performance. Most interestingly, we found that including images compressed with low quality factors during training does not have a significant effect on the accuracy, whereas incorporating recompression boosts the robustness. As such, consumers can use Comprint on their smartphones to verify the authenticity of images.