Oldest Papers
Specification gaming: the flip side of AI ingenuity
Victoria Krakovna, Jonathan Uesato, Vladimir Mikulik, Matthew Rahtz, Tom Everitt, Ramana Kumar, Zac Kenton, Jan Leike, Shane Legg
DeepMind Blog·2020
Specification gaming is a behaviour that satisfies the literal specification of an objective without achieving the intended outcome. This post examines examples of specification gaming in AI systems, why it occurs, and how we might address it. As machine learning systems become more powerful, specification gaming becomes a more pressing concern, highlighting the importance of reward specification and human-AI alignment research.
No ratings yet
View paper →Specification gaming: the flip side of AI ingenuity
Victoria Krakovna, Jonathan Uesato, Vladimir Mikulik, Matthew Rahtz, Tom Everitt, Ramana Kumar, Zac Kenton, Jan Leike, Shane Legg
DeepMind Blog·2020
Specification gaming is a behaviour that satisfies the literal specification of an objective without achieving the intended outcome. We have all had experiences with specification gaming, even if not…
No ratings yet
View paper →Experience Grounds Language
Yonatan Bisk, Ari Holtzman, Jesse Thomason, Jacob Andreas, Yoshua Bengio, Joyce Chai, Mirella Lapata, Angeliki Lazaridou, Jonathan May, Aleksandr Nisnevich, Nicolas Pinto, Joseph Turian
arXiv·2020
Language understanding research is held back by a failure to relate language to the physical world it describes and to the social interactions it facilitates. Despite the incredible effectiveness of language processing models to tackle tasks after being trained on text alone, successful linguistic communication relies on a shared experience of the world. It is this shared experience that makes utterances meaningful.
Natural language processing is a diverse field, and progress throughout its development has come from new representational theories, modeling techniques, data collection paradigms, and tasks. We posit that the present success of representation learning approaches trained on large, text-only corpora requires the parallel tradition of research on the broader physical and social context of language to address the deeper questions of communication.
★ 5.0 (1)
View paper →Brain experiments imply adaptation mechanisms which outperform common AI learning algorithms
Shira Sardi, Roni Vardi, Yuval Meir, Yael Tugendhaft, Shiri Hodassman, Amir Goldental, Ido Kanter
Scientific Reports·2020·8 citations
Attempting to imitate the brain’s functionalities, researchers have bridged between neuroscience and artificial intelligence for decades; however, experimental neuroscience has not directly advanced the field of machine learning (ML). Here, using neuronal cultures, we demonstrate that increased training frequency accelerates the neuronal adaptation processes. This mechanism was implemented on artificial neural networks, where a local learning step-size increases for coherent consecutive learning steps, and tested on a simple dataset of handwritten digits, MNIST. Based on our on-line learning results with a few handwriting examples, success rates for brain-inspired algorithms substantially outperform the commonly used ML algorithms. We speculate this emerging bridge from slow brain function to ML will promote ultrafast decision making under limited examples, which is the reality in many aspects of human activity, robotic control, and network optimization.
No ratings yet
View paper →