Ki In Der Industrie

Hochreiter's xLSTM paper was eagerly awaited. Now it is here. Quote: "We have enhanced LSTM to xLSTM by exponential gating with memory mixing and a new memory structure. xLSTM models perform favorably on language modeling when compared to state-of-the-art methods like Transformers and State Space Models. The scaling laws indicate that larger xLSTM models will be serious competitors to current Large Language Models that are built with the Transformer technology. xLSTM has the potential to considerably impact other deep learning fields like Reinforcement Learning, Time Series Prediction, or the modeling of physical systems." Industrial applications in particular are eyeing xLSTM. The next step is the commercial distribution of the architecture. We met Timo Gessmann, CTO of Schunk, at the Hannover Messe. He uses a GenAI approach to accelerate labeling. The Industrial AI Podcast reports weekly on the latest developments in AI and machine learning for the engineering, robotics, automotive, process and automatio