FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387058865> ?p ?o ?g. }

• W4387058865 abstract "The ventral visual processing hierarchy of the cortex needs to fulfill at least two key functions: perceived objects must be mapped to high-level representations invariantly of the precise viewing conditions, and a generative model must be learned that allows, for instance, to fill in occluded information guided by visual experience. Here, we show how a multilayered predictive coding network can learn to recognize objects from the bottom up and to generate specific representations via a top-down pathway through a single learning rule: the local minimization of prediction errors. Trained on sequences of continuously transformed objects, neurons in the highest network area become tuned to object identity invariant of precise position, comparable to inferotemporal neurons in macaques. Drawing on this, the dynamic properties of invariant object representations reproduce experimentally observed hierarchies of timescales from low to high levels of the ventral processing stream. The predicted faster decorrelation of error-neuron activity compared to representation neurons is of relevance for the experimental search for neural correlates of prediction errors. Lastly, the generative capacity of the network is confirmed by reconstructing specific object images, robust to partial occlusion of the inputs. By learning invariance from temporal continuity within a generative model, the approach generalizes the predictive coding framework to dynamic inputs in a more biologically plausible way than self-supervised networks with non-local error-backpropagation. This was achieved simply by shifting the training paradigm to dynamic inputs, with little change in architecture and learning rule from static input-reconstructing Hebbian predictive coding networks." @default.
• W4387058865 created "2023-09-27" @default.
• W4387058865 creator A5005914878 @default.
• W4387058865 creator A5012317571 @default.
• W4387058865 creator A5026319630 @default.
• W4387058865 creator A5038721084 @default.
• W4387058865 date "2023-09-25" @default.
• W4387058865 modified "2023-10-12" @default.
• W4387058865 title "Local minimization of prediction errors drives learning of invariant object representations in a generative network model of visual perception" @default.
• W4387058865 cites W1526492552 @default.
• W4387058865 cites W1855112655 @default.
• W4387058865 cites W1966342514 @default.
• W4387058865 cites W1990288127 @default.
• W4387058865 cites W1991362484 @default.
• W4387058865 cites W1996348120 @default.
• W4387058865 cites W2007997142 @default.
• W4387058865 cites W2015321847 @default.
• W4387058865 cites W2017040534 @default.
• W4387058865 cites W2021546183 @default.
• W4387058865 cites W2038032054 @default.
• W4387058865 cites W2043426395 @default.
• W4387058865 cites W2049364880 @default.
• W4387058865 cites W2049517487 @default.
• W4387058865 cites W2057641276 @default.
• W4387058865 cites W2060436934 @default.
• W4387058865 cites W2065821796 @default.
• W4387058865 cites W2066835186 @default.
• W4387058865 cites W2069922615 @default.
• W4387058865 cites W2071290167 @default.
• W4387058865 cites W2082627290 @default.
• W4387058865 cites W2089632738 @default.
• W4387058865 cites W2093002383 @default.
• W4387058865 cites W2095716305 @default.
• W4387058865 cites W2096388912 @default.
• W4387058865 cites W2101295242 @default.
• W4387058865 cites W2113299665 @default.
• W4387058865 cites W2119885245 @default.
• W4387058865 cites W2120079537 @default.
• W4387058865 cites W2122872927 @default.
• W4387058865 cites W2125663122 @default.
• W4387058865 cites W2127531110 @default.
• W4387058865 cites W2139048253 @default.
• W4387058865 cites W2142756981 @default.
• W4387058865 cites W2146444479 @default.
• W4387058865 cites W2147800946 @default.
• W4387058865 cites W2148764920 @default.
• W4387058865 cites W2149194912 @default.
• W4387058865 cites W2160654481 @default.
• W4387058865 cites W2168101731 @default.
• W4387058865 cites W2168202614 @default.
• W4387058865 cites W2413648480 @default.
• W4387058865 cites W2542327379 @default.
• W4387058865 cites W2566724240 @default.
• W4387058865 cites W2586591890 @default.
• W4387058865 cites W2604086949 @default.
• W4387058865 cites W2606274715 @default.
• W4387058865 cites W2755486058 @default.
• W4387058865 cites W2757870059 @default.
• W4387058865 cites W2766736793 @default.
• W4387058865 cites W2800603749 @default.
• W4387058865 cites W2898208057 @default.
• W4387058865 cites W2920861607 @default.
• W4387058865 cites W2965728926 @default.
• W4387058865 cites W2991252301 @default.
• W4387058865 cites W3008716087 @default.
• W4387058865 cites W3016954138 @default.
• W4387058865 cites W3029063334 @default.
• W4387058865 cites W3081068330 @default.
• W4387058865 cites W3093704180 @default.
• W4387058865 cites W3162322270 @default.
• W4387058865 cites W3184706608 @default.
• W4387058865 cites W3184778028 @default.
• W4387058865 cites W3202353721 @default.
• W4387058865 cites W3208311093 @default.
• W4387058865 cites W4213413356 @default.
• W4387058865 cites W4221074668 @default.
• W4387058865 cites W4281296081 @default.
• W4387058865 cites W4283365890 @default.
• W4387058865 cites W4285802298 @default.
• W4387058865 cites W4379517753 @default.
• W4387058865 cites W4384820554 @default.
• W4387058865 cites W64652264 @default.
• W4387058865 doi "https://doi.org/10.3389/fncom.2023.1207361" @default.
• W4387058865 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37818157" @default.
• W4387058865 hasPublicationYear "2023" @default.
• W4387058865 type Work @default.
• W4387058865 citedByCount "0" @default.
• W4387058865 crossrefType "journal-article" @default.
• W4387058865 hasAuthorship W4387058865A5005914878 @default.
• W4387058865 hasAuthorship W4387058865A5012317571 @default.
• W4387058865 hasAuthorship W4387058865A5026319630 @default.
• W4387058865 hasAuthorship W4387058865A5038721084 @default.
• W4387058865 hasBestOaLocation W43870588651 @default.
• W4387058865 hasConcept C105795698 @default.
• W4387058865 hasConcept C111437709 @default.
• W4387058865 hasConcept C119857082 @default.
• W4387058865 hasConcept C153180895 @default.
• W4387058865 hasConcept C154945302 @default.
• W4387058865 hasConcept C167966045 @default.
• W4387058865 hasConcept C179518139 @default.

• next