Continuous Thought Machines

This is the Continuous Thought Machine (CTM): a new type of neural network that uses the synchronization of neural activity over time as its representation for taking actions in a world. This maze solving demo runs a real CTM in your browser: it tries to find a path (up to 150 steps) from the red pixel to the green pixel. Hit the teleport button to move the start location to the last step the CTM predicts, and have fun teleporting to solve longer paths! You can also hit the run button to watch it solve again. You can move the start or end positions by clicking on different maze locations. Toggle the move button to switch between moving start or end positions. As it pays attention to the maze (shown below the maze and overlayed brightly) it unfolds Neural Dynamics: the complex, time-dependent patterns of neural activity. The way that neurons synchronize is how the CTM interacts with the world. Watch how it builds a route as it thinks. Have fun trying to solve these mazes quickly with th

--> This page requires Javascript. Please enable it to view the website. Continuous Thought Machines tl;dr Neurons in brains use timing and synchronization in the way that they compute. This property seems essential for the flexibility and adaptability of biological intelligence. Modern AI systems discard this fundamental property in favor of efficiency and simplicity. We found a way of bridging the gap between the existing powerful implementations and scalability of modern AI, and the biological plausibility paradigm where neuron timing matters . The results have been surprising and encouragi

saved by

• David Huang
• Abhi Upadhyay

related reading

• The Unreasonable Effectiveness of Recurrent Neural Networkskarpathy.github.io
• Aman's AI Journal • Primers • Ilya Sutskever's Top 30aman.ai
• The Computational Theory of Mind (Stanford Encyclopedia of Philosophy)plato.stanford.edu
• LLM Daydreaming · Gwern.netgwern.net
• Andrej Karpathy — AGI is still a decade awaydwarkesh.com
• Sequence Modeling with CTCdistill.pub
• Understanding LSTM Networks -- colah's blogcolah.github.io
• Memory makes computation universal, remember?thinks.lol
• NL.pdfabehrouz.github.io
• Neural Data Transformerarxiv.org
• Building machines that learn and think like people | Behavioral and Brain Sciences | Cambridge Corecambridge.org
• pdfopenreview.net