Researchers Comparing DNNs to Brains Need to Adopt Standard Methods of Science.
Dec 2, 2022
Speakers
Jeffrey Bowers
Speaker · 0 followers
About
The claim that DNNs and brains represent information in similar ways is largely based on the good performance of DNNs on various brain benchmarks. On this approach, the better DNNs can predict neural activity, the better the correspondence between DNNs and brains. But this is at odds with the standard scientific research approach that is characterized by varying independent variables to test specific hypotheses regarding the causal mechanisms that underlie some phenomenon; models are supported to the extent that they account for these experimental results. The best evidence for a model is that it survives “severe” tests, namely, experiments that have a high probability of falsifying a model if and only if the model is false in some relevant manner. When DNNs are assessed in this way, they catastrophically fail. The field needs to change its methods and put far more weight into falsification to get a better characterization of DNN-brain correspondences and to build more human-like AI.The claim that DNNs and brains represent information in similar ways is largely based on the good performance of DNNs on various brain benchmarks. On this approach, the better DNNs can predict neural activity, the better the correspondence between DNNs and brains. But this is at odds with the standard scientific research approach that is characterized by varying independent variables to test specific hypotheses regarding the causal mechanisms that underlie some phenomenon; models are supported t…
Organizer
NeurIPS 2022
Account · 966 followers
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
Estimating Noise Transition Matrix with Label Correlations for Noisy Multi-Label Learning
Watch later
Shikun Li, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
ProofNet: A Benchmark for Formal Theorem Proving and Autoformalization
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Lessons from Language Modeling for Embodied Teachable Agents
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
A Neural Pre-Conditioning Active Learning Algorithm to Reduce Label Complexity
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Optimizing Data Collection for Machine Learning
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Leaning Graph-embedded Key-event Back-tracing for Object Tracking in Event Clouds
Watch later
Zhiyu Zhu, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%