This research project investigates the application of deep learning to timbre transfer, where the timbre of a source audio can be converted to the timbre of a target audio with minimal loss in quality. The adopted approach combines Variational Autoencoders with Generative Adversarial Networks to construct meaningful representations of the source audio and produce realistic generations of the target audio and is applied to the Flickr 8k Audio dataset for transferring the vocal timbre between speakers and the URMP dataset for transferring the musical timbre between instruments. Furthermore, variations of the adopted approach are trained, and generalised performance is compared using the metrics SSIM (Structural Similarity Index) and FAD (Frech\'et Audio Distance). It was found that a many-to-many approach supersedes a one-to-one approach in terms of reconstructive capabilities, and that the adoption of a basic over a bottleneck residual block design is more suitable for enriching content information about a latent space. It was also found that the decision on whether cyclic loss takes on a variational autoencoder or vanilla autoencoder approach does not have a significant impact on reconstructive and adversarial translation aspects of the model.

How to Write a Blog Post in 10 Minutes or Less using A.I.: Writing blog posts can take up a significant amount of time. Whether you're creating a new blog post or editing an old one, it takes time to find the right words and phrases to use. To make the whole process a lot easier, you can use artificial intelligence (A.I.) to write your content. A.I. is actually a powerful tool that can save you a lot of time when creating content. If you're curious to know how A.I. works in blog post creation, keep reading.

The intersection of computer science, philosophy and neuroscience is perhaps the most fascinating destination today for artificial intelligence researchers.

Tiny flying drones, dubbed'slaughterbots', with facial recognition software and weapons capable of mass murder could be the future of warfare. A group of professors have warned the technology is already available to create flying mini killing machines. The Future of Life Institute (FLI), an artificial intelligence watchdog backed by the likes of physicist Stephen Hawking, has produced this chilling video demonstrating how these'slaughterbots' could kill thousands of people. The film is a vision of a dystopian future where tiny drones equipped with explosives, cameras, sensors and face scanners can programmed to carry out deathly instructions by either governments or terrorists. The UN Convention on Conventional Weapons summit in Geneva screened the film and also was heard stark warnings about the growing danger of drone warfare.

How data is represented and operationalized is critical for building computational solutions that are both effective and efficient. A common approach is to represent data objects as binary vectors, denoted \textit{hash codes}, which require little storage and enable efficient similarity search through direct indexing into a hash table or through similarity computations in an appropriate space. Due to the limited expressibility of hash codes, compared to real-valued representations, a core open challenge is how to generate hash codes that well capture semantic content or latent properties using a small number of bits, while ensuring that the hash codes are distributed in a way that does not reduce their search efficiency. State of the art methods use representation learning for generating such hash codes, focusing on neural autoencoder architectures where semantics are encoded into the hash codes by learning to reconstruct the original inputs of the hash codes. This thesis addresses the above challenge and makes a number of contributions to representation learning that (i) improve effectiveness of hash codes through more expressive representations and a more effective similarity measure than the current state of the art, namely the Hamming distance, and (ii) improve efficiency of hash codes by learning representations that are especially suited to the choice of search method. The contributions are empirically validated on several tasks related to similarity search and recommendation.

I am looking for computer vision tasks where the use of multi-scale feature extractors is crucial for performance. Links to studies establishing the importance of multi-scale features for any CV task would be much appreciated!

The application of methods based on artificial intelligence and machine learning opens the door to technology to diagnose Parkinson's.

This article is brought to you thanks to the collaboration of The European Sting with the World Economic Forum. One of the popular memes in literature, movies and tech journalism is that man's creation will rise and destroy it. Lately, this has taken the form of a fear of AI becoming omnipotent, rising up and annihilating mankind. The economy has jumped on the AI bandwagon; for a certain period, if you did not have "AI" in your investor pitch, you could forget about funding. However, is there actually anything deserving of the term AI?

Horror movies frequently feature a "final girl," a female character who survives to the end of the movie when most--or all--of the other characters do not. Stephen Graham Jones, author of My Heart Is a Chainsaw, is a big fan of the final girl trope. "The final girl is to the slasher as the silver bullet is to the werewolf, as daylight is to the vampire, as a headshot is to the zombie," Jones says in Episode 482 of the Geek's Guide to the Galaxy podcast. Geek's Guide to the Galaxy host David Barr Kirtley says that final girls tap into our natural tendency to root for the underdog. "It's more of an accomplishment for a young woman to defeat the bad guy than if it's some experienced, buff soldier," he says.

You can ask Amazon's virtual assistant, Alexa, for a lot of things. To play music, read the news or tell you the weather. You can even ask her to define "artificial intelligence." "Artificial intelligence," Alexa says, "is the ability of a computer program or a machine to think or learn." What Alexa fails to mention is that she herself is a form of artificial intelligence.