Is this mind-reading AI tool surpassing Elon Musk’s Neuralink by converting thoughts into text?

The University of Technology Sydney’s GrapheneX-UTS Human-centric Artificial Intelligence Centre has developed a groundbreaking device known as the world’s first mind-reading helmet. This incredible invention utilizes artificial intelligence to translate silent thoughts into written text, providing a crucial means of communication for individuals who are unable to speak due to conditions like paralysis or stroke. Moreover, it has the potential to revolutionize human-machine interaction, allowing for improved control over robots and bionic arms. The device operates by capturing brain activity through an electroencephalogram (EEG) equipped cap worn by participants. The brain waves are then analyzed by an AI model called DeWave, which accurately converts them into coherent written messages. A video demonstration showcased the helmet’s ability to accurately render complex thoughts into written form. With the continuous advancements in AI, the possibilities for this tool are limitless.

Coding techniques in brain-to-text translation

GrapheneX-UTS HAI Center Director CT Lin led the research, emphasizing the pioneering nature of the work. This breakthrough involves separate coding techniques for brain-to-text translation, pushing the boundaries of neural decoding. Integration with large language models opens new frontiers for neuroscience and artificial intelligence. You can find out about the research here.

Although EEG signals from the cap result in a noisier output compared to implanted electrodes, the study exceeded previous benchmarks in EEG translation. The researchers highlighted the non-invasive, cost-effective and easily transportable nature of their technology, setting it apart from Elon Musk’s Neuralink, a brain chip startup that is in human trials for paralysis patients.

Musk’s Neuralink aims to surgically place brain-computer interface (BCI) implants, which will initially allow control of a computer cursor or keyboard through thoughts alone. Musk envisions broader applications, including for treating obesity, autism, depression and schizophrenia. However, it has raised several ethical concerns as it has reportedly caused harm and even death to animals in experiments. The helmet is clearly free of these concerns, and the increasing success rate makes it a great competitor to Neuralink.

So how does this differ from Neuralink’s brain implants? It’s definitely not bleeding. Here’s how it’s done.

How is it done

1. Participants read excerpts of text silently while wearing a helmet

2. It recorded electrical brain activity through their scalps

3. This is done using the old fashioned electroencephalogram (EEG).

4. The EEG wave is segmented into separate units

5. These then capture certain characteristics and patterns of the human brain. This is done by an artificial intelligence model developed by researchers called DeWave.

6. What it does is translate the EEG signals into words and sentences.

7. However, this is only possible after learning from large amounts of EEG data.

8. In fact, it incorporates separate coding techniques in the brain-to-text translation process and presents an innovative approach to neural decoding.

Distinguished Professor Lin said: “This research represents pioneering work in translating raw EEG waves directly into language, marking a significant breakthrough in the field”. He added: “Integration with large language models also opens up new frontiers for neuroscience and artificial intelligence.”