Phase transitions in when feedback is useful
Nov 28, 2022
Speakers
Lokesh Boominathan
Speaker · 0 followers
Xaq Pitkow
Speaker · 0 followers
About
Sensory observations about the world are invariably ambiguous. Inference about the world's latent variables is thus an important computation for the brain. However, computational constraints limit the performance of these computations. These constraints include energetic costs for neural activity and noise on every channel. Efficient coding is one prominent theory that describes how such limited resources can best be used. In one incarnation, this leads to a theory of predictive coding, where predictions are subtracted from signals, reducing the cost of sending something that is already known. This theory does not, however, account for the costs or noise associated with those predictions. Here we offer a theory that accounts for both feedforward and feedback costs, and noise in all computations. We formulate this inference problem as message-passing on a graph whereby feedback serves as an internal control signal aiming to maximize how well an inference tracks a target state while minimizing the costs of computation. We apply this novel formulation of inference as control to the canonical problem of inferring the hidden scalar state of a linear dynamical system with Gaussian variability. The best solution depends on architectural constraints, such as Dale's law, the ubiquitous law that each neuron makes solely excitatory or inhibitory postsynaptic connections. This biological structure can create asymmetric costs for feedforward and feedback channels. Under such conditions, our theory predicts the gain of optimal predictive feedback and how it is incorporated into the inference computation. We show that there is a non-monotonic dependence of optimal feedback gain as a function of both the computational parameters and the world dynamics, leading to phase transitions in whether feedback provides any utility in optimal inference under computational constraints.Sensory observations about the world are invariably ambiguous. Inference about the world's latent variables is thus an important computation for the brain. However, computational constraints limit the performance of these computations. These constraints include energetic costs for neural activity and noise on every channel. Efficient coding is one prominent theory that describes how such limited resources can best be used. In one incarnation, this leads to a theory of predictive coding, where pr…
Organizer
NeurIPS 2022
Account · 952 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
Ensemble of Averages: Improving Model Selection and Boosting Performance in Domain Generalization
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Scalable and Efficient Non-adaptive Deterministic Group Testing
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
A Transformer-Based Object Detector with Corse-Fine Crossing Representations
Watch later
Zhishan Li, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
AlphaTensor: Discovering faster matrix multiplication algorithms with RL
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
MaskPlace: Fast Chip Placement via Reinforced Visual Representation Learning
Watch later
Yao Lai, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Decimated Framelet System on Graphs and Fast G-Framelet Transforms
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%