学进去

Mind-reading AI turns thoughts into words using a brain implant

An artificial intelligence can accurately translate thoughts into sentences, at least for a limited vocabulary of 250 words. The system may bring us a step closer to _________ speech to people who have lost the ability because of paralysis.

Joseph Makin at the University of California, San Francisco, and his colleagues used deep learning algorithms to study the brain _________ of four women as they spoke. The women, who all have epilepsy, already had electrodes attached to their brains to _________ seizures. Each woman was asked to read aloud from a set of sentences as the team measured brain activity. The largest group of sentences _________ 250 unique words.

The team fed this brain activity to a neural network algorithm, training it to identify regularly _________ patterns that could be linked to repeated aspects of speech, such as vowels or consonants. These patterns were then fed to a second neural network, which tried to turn them into words to _________ a sentence.

Each woman repeated the sentences at least twice, and the final repetition didn’t form part of the training data, _________ the researchers to test the system. Each time a person speaks the same sentence, the brain activity associated will be similar but not identical. “Memorising the brain activity of the these sentences wouldn’t help, so the network instead has to learn what’s similar about them so that it can generalise to this final example,” says Makin. Across the four women, the AI’s best _________ was an average translation error rate of 3 percent.

Makin says that using a small number of sentences made it easier for the AI to learn which words tend to follow others. For example, the AI was able to decode that the word “Turner” was always likely to follow the word “Tina” in this set of sentences, from brain _________ alone.

The team tried decoding the brain signal data into __________ words at time, rather than whole sentences, but this increased the error rate to 38 per cent even for the best performance. “So the network clearly is learning facts about which words go together, and not just which neural activity __________ to which words,” says Makin. This will make it hard to __________ the system to a larger vocabulary because each new word increases the number of possible sentences, reducing __________.

Making says 250 words could still be useful for people who can’t talk. “We want to deploy this in a patient with an actual speech disability,” he says, although it is possible their brain activity may be different from that of the women in this study, making this more __________.

Sophie Scott at University College London says we are a long way from being able to translate brain signal data comprehensively. “You probably know around 250, 000 words, so it’s still an incredibly __________ set of speech that they’re using,” she says.