AI_ML_DL’s diary


Building machines that learn and think like people

Building machines that learn and think like people

B. M. Lake et al., CoRR 2016


The Measure of Intelligenceの引用文献[51]



F. Schollet氏の論文では、次のように引用している。

We also argue, in agreement with [51], that general AI systems should hard-code as fundamental priors these core knowledge principles.



6.3 Towards more human-like learning and thinking machines
     Since the birth of AI in the 1950s, people have wanted to build machines that learn and think like people. We hope researchers in AI, machine learning, and cognitive science will accept our challenge problems as a testbed for progress. Rather than just building systems that recognize handwritten characters and play Frostbite or Go as the end result of an asymptotic process, we suggest that deep learning and other computational paradigms should aim to tackle these tasks using as little training data as people need, and also to evaluate models on a range of human-like generalizations beyond the one task the model was trained on. We hope that the ingredients outlined in this article will
prove useful for working towards this goal: seeing objects and agents rather than features, building causal models and not just recognizing patterns, recombining representations without needing to retrain, and learning-to-learn rather than starting from scratch.






これを読む時間があるなら、The Measure of Intelligenceを深読みする方が良い。





style=119 iteration=1


style=119 iteration=20


style=119 iteration=500