Goto

Collaborating Authors

video


AI Synthetic Media: What to expect and what it will mean

#artificialintelligence

AI learns from seen data to make predictions about unseen data. What is utterly remarkable is that prediction can underpin extraordinary creativity and mimicry. These developments have the potential to unleash an explosion of scale creativity -- delivering content design and production tools into the hands of the mass market that have hitherto only been available to large corporations with hefty budgets. Even now -- when we are still in the infancy of AI media generation -- there are demos, apps and subscription-based services to faceswap individuals into movies (see Zao), turn rough sketches into photorealistic images (try the GauGAN demo here), convert one voice into another (see Respeecher), personalise marketing videos (try the Synthesia demo here), age- and emotion-alter images (see Photoshop's new Neural Filters), generate face-synched videos of new or translated scripts (see Canny AI), play a video game with characters speaking any of 10 face-synched languages (see Cyberpunk 2077), and play a text-based adventure game with endless dialogue generated by AI (try out the free version of AI Dungeon here). Moreover, the same AI techniques will spawn new applications in a wide range of fields: advertising, architecture, interior design, gaming, song-writing, web design, education, even software development and pure mathematics -- in fact anywhere where structured or constrained creativity is key.


DJI unveils the Air 2S drone with 20-megapixel camera

Engadget

It's barely been a month since DJI unveiled a new drone, and the company already has another to show. Note the absence of the Mavic branding, indicating we might be seeing more of a shift in how the company pitches each level of quadcopter it offers. It's not clear if the "S" branding here is an Apple-style upgrade to the previous model, but the Air 2S certainly looks like someone gave the previous model a light facelift. The design seems near-identical bar a few smoother lines and an extra pair of front obstacle avoidance cameras. But what's important here is the camera it seems.


DJI's New Drone Makes Aerial Cinematography a Breeze

WIRED

DJI has a new drone, the Air 2S, and it's one of the best drones I've ever flown. The Air 2S is externally nearly identical to last year's Mavic Air 2. It even uses the same batteries, which makes upgrading a little cheaper. There are some very welcome changes in this update. The Air 2S adds an object detection camera to the top of the drone, which improves the collision avoidance system. It really helps when you're flying toward something at high speed, since the drone pitches forward, rendering the front sensor slightly less effective.


Deep Learning vs Machine Learning

#artificialintelligence

Machine Learning and Deep Learning are concepts that are often overlapping. There can be a slight confusion between the terms, and thus, let us look at Machine learning vs Deep learning, and understand the similarities and differences between the same. Machine learning uses a set of algorithms to analyse and interpret data, learn from it, and based on the learnings, make best possible decisions. On the other hand, Deep learning structures the algorithms into multiple layers in order to create an "artificial neural network". This neural network can learn from the data and make intelligent decisions on its own.


Elon Musk's brain-implant lab claims this poor monkey's playing 'Pong' with its mind

Mashable

Elon Musk's brain-implant lab, Neuralink, today released video appearing to show something the tech billionaire has been bragging about since 2019: a monkey playing a video game ... with its mind. In the video (and an accompanying one of the Neuralink signal readout, if you're into that), a rhesus macaque named Pager is shown playing simple games on a screen while sucking on a straw that's delivering a tasty banana smoothie as a reward. Pager, at first, uses a joystick to move a dot around a grid, placing it onto squares that light up one by one at random. In the next sequence, he's still using the joystick -- but as the gently British-accented narrator points out, the joystick apparatus is quite clearly unplugged. The implant, we're told, is transmitting data from the electrical signals his brain emits as he plays.


Computer vision development platform CrowdAI raises $6.25M

#artificialintelligence

Register for a free or VIP pass today. CrowdAI, a computer vision development platform, today announced that it closed a $6.25 million series A financing round led by Threshold Ventures. The fundraising coincides with the launch of the startup's new solution that allows customers to create AI that analyzes images and videos. The AI skills gap remains a significant impediment to adoption in most enterprises, a 2020 O'Reilly survey found. Slightly more than one-sixth of respondents cited difficulty in hiring experts as a barrier to AI deployment in their organizations.


Google Nest Hub (2nd gen) review: wearable-free sleep tracking smart display

The Guardian

Google's second-generation Nest Hub smart display now comes with radar-based sleep tracking as it attempts to keep Amazon's Alexa at bay. The new Nest Hub costs £89.99 on launch, which makes it cheaper than its predecessor and slightly undercuts competitors of a similar size. The second-generation unit has the same design as the original but is ever-so-slightly taller. The 7in LCD screen looks great and is crisp enough for viewing at arm's length or further, making it perfect for use as a digital photo frame. The body is now made of recycled plastic and the screen is covered in an edgeless glass, which makes it easier to wipe clean.


Women's pain 'perceived as less intense' than men's pain

Daily Mail - Science & tech

Pain felt by women is perceived as less intense by observers as pain felt by men, a new study reveals. US scientists found that when male and female patients experienced the same amount of pain, observers viewed female patients' pain as milder and more likely to benefit from psychotherapy than medication. Both male and female observers were found to be guilty of this'gender bias', which could lead to disparities in treatments and women in pain not getting the medication they need. According to the experts, the bias is due to an age-old stereotype that men are more'stoic' that women – and so their pain is likely to be more serious. University of Miami researchers found that when male and female patients expressed the same amount of pain, observers viewed female patients' pain as less intense and more likely to benefit from psychotherapy versus medication as compared to men's pain, exposing a significant patient gender bias that could lead to disparities in treatments (stock image) Health professionals use different terms for different types of pain.


6 of the best dating sites for people who love Pornhub

Mashable

It's no secret that people love porn, with thousands of users watching pornography on the internet every second (Pornhub saw 42 billion site visits in 2019 alone). With just a few clicks on your smartphone, tablet, or computer, you can enjoy an endless world of hot and steamy images and videos in every conceivable genre. Even in today's social distancing climate, your dating and sex life doesn't need to dry up or be boring. But with recent allegations of child pornography, revenge porn, and rape coming out against the parent company of Pornhub -- one of the largest players in the free porn game -- it might be time for some alternative programming. If you like porn but want to make things a bit more interactive, these are some popular dating sites that will help you achieve that.


shobrook/sequitur

#artificialintelligence

It implements three different autoencoder architectures in PyTorch, and a predefined training loop. Each autoencoder learns to represent input sequences as lower-dimensional, fixed-size vectors. This can be useful for finding patterns among sequences, clustering sequences, or converting sequences into inputs for other algorithms. First, you need to prepare a set of example sequences to train an autoencoder on. So, if each example in your training set is a sequence of 10 5x5 matrices, then each example would be a tensor with shape [10, 5, 5].