Machine translation of cortical activity to text with an encoder–decoder framework https://www.nature.com/articles/s41593-020-0608-8

• Training a recurrent neural network to encode each sentence-length sequence of neural activity into an abstract representation, and then to decode this representation, word by word, into an English sentence.

Takeshi Kojima, Shixiang Shane Gu, Machel Reid, Yutaka Matsuo, Yusuke Iwasawa , Large Language Models are Zero-Shot Reasoners, ICML 2022 Workshop KRLM, arXiv:2205.11916. Available from: https://arxiv.org/abs/2205.11916

• Numerous experiments show that Large language models (LLMs) are just parroting their training data and are only showing impressive results because they have been exposed to huge amounts of text and break as soon as they are presented with tasks and problems that require reasoning, common sense, and skills that are implicitly learned. But this study shows that if you provide the LLMs with well-crafted prompts, you can steer them toward answering questions that require reasoning and step-by-step thinking. The researchers present a method called “zero-shot chain-of-thought” prompting, which uses a special trigger phrase in the prompt to force the LLM to go through the steps required to solve problems. And although simple, the method seems to work well frequently.

Papastratis I, Chatzikonstantinou C, Konstantinidis D, Dimitropoulos K, Daras P. Artificial Intelligence Technologies for Sign Language. Sensors (Basel). 2021 Aug 30;21(17):5843. doi: 10.3390/s21175843. PMID: 34502733; PMCID: PMC8434597. Available from: https://www.mdpi.com/1424-8220/21/17/5843

• This survey provides a comprehensive review of state-of-the-art methods in sign language capturing, recognition, translation and representation, pinpointing their advantages and limitations. In addition, the survey presents a number of applications, while it discusses the main challenges in the field of sign language technologies.