3D Printing Functional Human Brain Tissue For Research Purposes

February 12, 2024 by Maya Posch 18 Comments

Graphical summary of the newly developed 3D bioprinting process. (Credit: Yan et al., 2024)

The brain is probably the least explored organ, much of which is due to the difficulty of studying it in situ rather than in slices under a microscope. Even growing small organoids out of neurons provide few clues, as this is not how brain tissue is normally organized. A possible breakthrough may have been found here by a group of researchers whose article in Cell Stem Cell details how they created functional human neural tissues using a commercial 3D bioprinter.

As detailed by [Yuanwei Yan] and colleagues in their research article, the issue with previous approaches was that although these would print layers of neurons, they would fail to integrate as in the brain. In the brain’s tissues, we see a wide variety of neurons and supportive cells, all of which integrate in a specific way to form functioning neuron-to-neuron and neuron-to-glial connections with expected neural activity. The accomplishment of this research team is 3D bioprinting of neural tissues with the necessary functional connections.

Continue reading “3D Printing Functional Human Brain Tissue For Research Purposes” →

Deep Learning Enables Intuitive Prosthetic Control

May 27, 2021 by Lewin Day 7 Comments

Prosthetic limbs have been slow to evolve from simple motionless replicas of human body parts to moving, active devices. A major part of this is that controlling the many joints of a prosthetic is no easy task. However, researchers have worked to simplify this task, by capturing nerve signals and allowing deep learning routines to figure the rest out.

The prosthetic arm under test actually carries a NVIDIA Jetson Nano onboard to run the AI nerve signal decoder algorithm.

Reported in a pre-published paper, researchers used implanted electrodes to capture signals from the median and ulnar nerves in the forearm of Shawn Findley, who had lost a hand to a machine shop accident 17 years prior. An AI decoder was then trained to decipher signals from the electrodes using an NVIDIA Titan X GPU.

With this done, the decoder model could then be run on a significantly more lightweight system consisting of an NVIDIA Jetson Nano, which is small enough to mount on a prosthetic itself. This allowed Findley to control a prosthetic hand by thought, without needing to be attached to any external equipment. The system also allowed for intuitive control of Far Cry 5, which sounds like a fun time as well.

The research is exciting, and yet another step towards full-function prosthetics becoming a reality. The key to the technology is that models can be trained on powerful hardware, but run on much lower-end single-board computers, avoiding the need for prosthetic users to carry around bulky hardware to make the nerve interface work. If it can be combined with a non-invasive nerve interface, expect this technology to explode in use around the world.

[Thanks to Brian Caulfield for the tip!]

Seeing-Eye Shoes Pair Computer Vision With Haptic Feedback

May 12, 2021 by Kristina Panos 21 Comments

Over the years, we’ve seen plenty of projects that use ultrasonic or time-of-flight sensors as object detection methods for the visually impaired. Ultrasonic sensors detect objects like sonar — they send sound pulses and measure the time it takes for the signal to bounce off the object and come back. Time-of-flight sensors do essentially the same thing, but with infrared light. In either case, the notifications often come as haptic feedback on the wrist or head or whatever limb the ultrasonic module is attached to. We often wonder why there aren’t commercially-made shoes that do this, but it turns out there are, and they’re about to get even better.

The shoe’s view — safe walking space is delimited with color. Image via TU Graz

Today, Tec-Innovation makes shoes with ultrasonic sensors on the toes that can detect objects up to four meters away. The wearer is notified of obstacles through haptic feedback in the shoes as well as an audible phone notification via Bluetooth. The company teamed up with the Graz University of Technology in Austria to give the shoes robot vision that provides even better detail.

Ultrasonic is a great help, but it can’t detect the topography of the obstacle and tell a pothole from a rock from a wall. But if you have a camera on both feet, you can use the data to determine obstacle types and notify the user accordingly. These new models will still have the ultrasonic sensors to do the initial object detection, and use the cameras for analysis.

Whenever they do come out, the sensors will all be connected through the app, which paves the way for crowdsourced obstacle maps of various cities. The shoes will also be quite expensive. Can you do the same thing for less? Consider the gauntlet thrown!

We could all use some navigational help sometimes. Don’t want to look like a tourist? Get turn-by-turn directions in the corner of your eye.

Thanks for the tip, [Qes]!

Sufficiently Advanced Technology And Justice

December 5, 2020 by Elliot Williams 74 Comments

Imagine that you’re serving on a jury, and you’re given an image taken from a surveillance camera. It looks pretty much like the suspect, but the image has been “enhanced” by an AI from the original. Do you convict? How does this weigh out on the scales of reasonable doubt? Should you demand to see the original?

AI-enhanced, upscaled, or otherwise modified images are tremendously realistic. But what they’re showing you isn’t reality. When we wrote about this last week, [Denis Shiryaev], one of the authors of one of the methods we highlighted, weighed in the comments to point out that these modifications aren’t “restorations” of the original. While they might add incredibly fine detail, for instance, they don’t recreate or restore reality. The neural net creates its own reality, out of millions and millions of faces that it’s learned.

And for the purposes of identification, that’s exactly the problem: the facial features of millions of other people have been used to increase the resolution. Can you identify the person in the pixelized image? Can you identify that same person in the resulting up-sampling? If the question put before the jury was “is the defendant a former president of the USA?” you’d answer the question differently depending on which image you were presented. And you’d have a misleading level of confidence in your ability to judge the AI-retouched photo. Clearly, informed skepticism on the part of the jury is required.

Unfortunately, we’ve all seen countless examples of “zoom, enhance” in movies and TV shows being successfully used to nab the perps and nail their convictions. We haven’t seen nearly as much detailed analysis of how adversarial neural networks create faces out of a scant handful of pixels. This, combined with the almost magical resolution of the end product, would certainly sway a jury of normal folks. On the other hand, the popularity of intentionally misleading “deep fakes” might help educate the public to the dangers of believing what they see when AI is involved.

This is just one example, but keeping the public interested in and educated on the deep workings and limitations of the technology that’s running our world is more important than ever before, but some of the material is truly hard. How do we separate the science from the magic?

“Enhance” Is Now A Thing, But Don’t Believe What You See

November 25, 2020 by Lewin Day 64 Comments

It was a trope all too familiar in the 1990s — law enforcement in movies and TV taking a pixellated, blurry image, and hitting the magic “enhance” button to reveal suspects to be brought to justice. Creating data where there simply was none before was a great way to ruin immersion for anyone with a modicum of technical expertise, and spoiled many movies and TV shows.

Of course, technology marches on and what was once an utter impossibility often becomes trivial in due time. These days, it’s expected that a sub-$100 computer can easily differentiate between a banana, a dog, and a human, something that was unfathomable at the dawn of the microcomputer era. This capability is rooted in the technology of neural networks, which can be trained to do all manner of tasks formerly considered difficult for computers.

With neural networks and plenty of processing power at hand, there have been a flood of projects aiming to “enhance” everything from low-resolution human faces to old film footage, increasing resolution and filling in for the data that simply isn’t there. But what’s really going on behind the scenes, and is this technology really capable of accurately enhancing anything?

Continue reading ““Enhance” Is Now A Thing, But Don’t Believe What You See” →

Training A Neural Network To Play A Driving Game

November 7, 2020 by Lewin Day 12 Comments

Often, when we think of getting a computer to complete a task, we contemplate creating complex algorithms that take in the relevant inputs and produce the desired behaviour. For some tasks, like navigating a car down a road, the sheer multitude of input data and its relationship to the desired output is so complex that it becomes near-impossible to code a solution. In these cases, it can make more sense to create a neural network and train the computer to do the job, as one would a human. On a more basic level, [Gigante] did just that, teaching a neural network to play a basic driving game with a genetic algorithm.

The game consists of a basic top-down 2D driving game. The AI is given the distance to the edge of the track along five lines at different angles projected from the front of the vehicle. The AI also knows its speed and direction. Given these 7 numbers, it calculates the outputs for steering, braking and acceleration to drive the car.

To train the AI, [Gigante] started with 650 AIs, and picked the best performer, which just barely managed to navigate the first two corners. Marking this AI as the parent of the next generation, the AIs were iterated with random mutations. Each generation showed some improvement, with [Gigante] picking the best performers each time to parent the next generation. Within just four iterations, some of the cars are able to complete a full lap. With enough training, the cars are able to complete the course at great speed without hitting the walls at all.

It’s a great example of machine learning and the use of genetic algorithms to improve fitness over time. [Gigante] points out that there’s no need for a human in the loop either, if the software is coded to self-measure the fitness of each generation. We’ve seen similar techniques used to play Mario, too. Video after the break.

Continue reading “Training A Neural Network To Play A Driving Game” →

Generating Beetles From Public Domain Images

January 12, 2020 by Sharon Lin 11 Comments

Ever since [Ian Goodfellow] and his colleagues invented the generative adversarial network (GAN) in 2014, hundreds of projects, from style transfers to poetry generators, have been produced using the concept of contesting neural networks. Unlike traditional neural networks, GANs can generate new data that fits statistically within the same set as the training set.

[Bernat Cuni], the one-man design team behind [cunicode] came up with the idea to generate beetles using this technique. Inspired by material published on Machine Learning for Artists, he decided to deploy some visual experiments with zoological illustrations. The training data was found from a public domain book hosted at archive.org, found through the Biodiversity Heritage Library. A combination of OpenCV and ImageMagick helped with individually extracting illustrations to squared images.

[Cuni] then ran a DCGAN with the data set, generating the first set of quasi-beetles after some tinkering with epochs and settings. After the failed first experiment, he went with StyleGAN, setting up a machine at PaperSpace with 1 GPU and running the training for >3 days on 128 px images. The results were much better, but fairly small and the cost of running the machine was quite expensive (>€125).

Given the success of the previous experiment, he decided to transfer over to Google CoLab, using their 12 hours of K80 GPU per run for free to generate some more beetles. With the intent on producing more HD beetles, he used Runway trained on 1024 px beetles, discovering much better results after 3000 steps. The model was moved over to Google CoLab to produce HD outputs.

He has since continued to experiment with the beetles, producing some confusing generated images and fun collectibles.

Continue reading “Generating Beetles From Public Domain Images” →