Listen To The Netherworld With Artificial Intelligence

October 24, 2017 by Dan Maloney 19 Comments

It’s that time of year again, and with Halloween arguably being the hacker’s perfect holiday, we’re starting to see a tick up in projects with a spooky theme. Most seem to do with making some otherwise tame Halloween decorations scarily awesome, but this is different — using artificial intelligence to search for ghosts.

It seems like [Matt Reed]’s “DeepWhisper” project is meant to be taken as light-hearted fun for the spooky season, but there may be a touch of seriousness to his efforts to listen in on ghostly conversations. The principle behind this is electronic voice phenomena (EVP), whereby the metabolically and/or dimensionally challenged are purported to influence electronic systems, resulting in heavily processed audio clips that seem to have a whispered endearment from the departed or a threat from a malevolent spirit. DeepWhisper takes this a step further by using a Raspberry Pi to feed audio into the Google Cloud Speech API for analysis. If anything is whispered in one of the 110 or so languages Google knows, it’ll get displayed on a screen. [Matt] plans to set DeepWhisper up in the aptly-named Butchertown section of Nashville and live-stream the results next week.

It’ll be interesting to see what Google’s neural network makes out of the random noise it will probably only ever hear. And [Matt] is planning on releasing his code for all to see, so there may be some valuable cloud techniques to learn from DeepWhisper. But in the unlikely event that he does discover ghosts, it’s nice to know you can have the tools and the talent to bust ’em.

Continue reading “Listen To The Netherworld With Artificial Intelligence” →

Artificial Intelligence At The Top Of A Professional Sport

October 20, 2017 by Lauren Faris 20 Comments

The lights dim and the music swells as an elite competitor in a silk robe passes through a cheering crowd to take the ring. It’s a blueprint familiar to boxing, only this pugilist won’t be throwing punches.

OpenAI created an AI bot that has beaten the best players in the world at this year’s International championship. The International is an esports competition held annually for Dota 2, one of the most competitive multiplayer online battle arena (MOBA) games.

Each match of the International consists of two 5-player teams competing against each other for 35-45 minutes. In layman’s terms, it is an online version of capture the flag. While the premise may sound simple, it is actually one of the most complicated and detailed competitive games out there. The top teams are required to practice together daily, but this level of play is nothing new to them. To reach a professional level, individual players would practice obscenely late, go to sleep, and then repeat the process. For years. So how long did the AI bot have to prepare for this competition compared to these seasoned pros? A couple of months.

Continue reading “Artificial Intelligence At The Top Of A Professional Sport” →

AI: This Decade’s Worst Buzz Word

September 18, 2017 by Al Williams 84 Comments

In hacker circles, the “Internet of Things” is often the object of derision. Do we really need the IoT toaster? But there’s one phrase that — while not new — is really starting to annoy me in its current incarnation: AI or Artificial Intelligence.

The problem isn’t the phrase itself. It used to mean a collection of techniques used to make a computer look like it was smart enough to, say, play a game or hold a simulated conversation. Of course, in the movies it means HAL9000. Lately, though, companies have been overselling the concept and otherwise normal people are taking the bait.

The Alexa Effect

Not to pick on Amazon, but all of the home assistants like Alexa and Google Now tout themselves as AI. By the most classic definition, that’s true. AI techniques include matching natural language to predefined templates. That’s really all these devices are doing today. Granted the neural nets that allow for great speech recognition and reproduction are impressive. But they aren’t true intelligence nor are they even necessarily direct analogs of a human brain.

Continue reading “AI: This Decade’s Worst Buzz Word” →

Raspberry Pi AI Plays Piano

September 6, 2017 by Al Williams 7 Comments

[Zack] watched a video of [Dan Tepfer] using a computer with a MIDI keyboard to do some automatic fills when playing. He decided he wanted to do better and set out to create an AI that would learn–in real time–how to insert style-appropriate tunes in the gap between the human performance.

If you want the code, you can find it on GitHub. However, the really interesting part is the log of his experiences, successes, and failures. If you want to see the result, check out the video below where he riffs for about 30 seconds and the AI starts taking over for the melody when the performer stops.

Continue reading “Raspberry Pi AI Plays Piano” →

AI Watches You Sleep; Knows When You Dream

August 29, 2017 by James Hobson 5 Comments

If you’ve never been a patient at a sleep laboratory, monitoring a person as they sleep is an involved process of wires, sensors, and discomfort. Seeking a better method, MIT researchers — led by [Dina Katabi] and in collaboration with Massachusetts General Hospital — have developed a device that can non-invasively identify the stages of sleep in a patient.

Approximately the size of a laptop and mounted on a wall near the patient, the device measures the minuscule changes in reflected low-power RF signals. The wireless signals are analyzed by a deep neural-network AI and predicts the various sleep stages — light, deep, and REM sleep — of the patient, negating the task of manually combing through the data. Despite the sensitivity of the device, it is able to filter out irrelevant motions and interference, focusing on the breathing and pulse of the patient.

What’s novel here isn’t so much the hardware as it is the processing methodology. The researchers use both convolutional and recurrent neural networks along with what they call an adversarial training regime:

Our training regime involves 3 players: the feature encoder (CNN-RNN), the sleep stage predictor, and the source discriminator. The encoder plays a cooperative game with the predictor to predict sleep stages, and a minimax game against the source discriminator. Our source discriminator deviates from the standard domain-adversarial discriminator in that it takes as input also the predicted distribution of sleep stages in addition to the encoded features. This dependence facilitates accounting for inherent correlations between stages and individuals, which cannot be removed without degrading the performance of the predictive task.

Anyone out there want to give this one a try at home? We’d love to see a HackRF and GNU Radio used to record RF data. The researchers compare the RF to WiFi so repurposing a 2.4 GHz radio to send out repeating uniformed transmissions is a good place to start. Dump it into TensorFlow and report back.

Continue reading “AI Watches You Sleep; Knows When You Dream” →

Neural Nets In The Browser: Why Not?

August 4, 2017 by Al Williams 16 Comments

We keep seeing more and more Tensor Flow neural network projects. We also keep seeing more and more things running in the browser. You don’t have to be Mr. Spock to see this one coming. TensorFire runs neural networks in the browser and claims that WebGL allows it to run as quickly as it would on the user’s desktop computer. The main page is a demo that stylizes images, but if you want more detail you’ll probably want to visit the project page, instead. You might also enjoy the video from one of the creators, [Kevin Kwok], below.

TensorFire has two parts: a low-level language for writing massively parallel WebGL shaders that operate on 4D tensors and a high-level library for importing models from Keras or TensorFlow. The authors claim it will work on any GPU and–in some cases–will be actually faster than running native TensorFlow.

Continue reading “Neural Nets In The Browser: Why Not?” →

A Neural Network Can Now Be Your Writing Assistant

July 14, 2017 by Cameron Coward 15 Comments

Writing is a difficult job; though, as a primarily word-based site, we may be a little biased here at Hackaday. Not only does a writer have to know the basics, like what a semicolon is and when to use one, they also need to build sentences that convey information in a manner that is pleasant to read. As many commenters like to point out, even we struggle with this on occasion (lauded and scholarly as we are).

Wouldn’t it be better if we could let our computers do the heavy lifting for us? After all, a monkey with infinite time will eventually write Shakespeare and all that. Surely, a computer can be programmed to do all that fancy word assembly while we sit back and enjoy some coffee. Well, that’s what [Robin Sloan] set out to do with a recurrent neural network-powered writing assistant.

Alright, so it doesn’t actually write completely on its own. Instead, [Robin’s] software takes advantage of [JC Johnson’s] torch-rnn project, and integrates it into Atom to autocomplete sentences. [Robin] trained his neural network on hundreds of old issues of the sci-fi magazines Galaxy and IF Magazine, which are available at the Internet Archive. Once the server and corresponding Atom package are installed, a writer can simply push the Tab key and the sentence will be completed.

The results are interesting. [Robin] himself says “it’s like writing with a deranged but very well-read parrot on your shoulder.” While it’s not likely to be used as a serious writing tool anytime soon, the potential is certainly intriguing. When trained on relevant source material, the integration into software like Atom could be very useful. If a neural network can compose music, surely it can write some silly tech articles.

[thanks to Tim Trzepacz for the tip!]

Typewriter image: LjL (Public domain).