Publication
] Co-occurrence statistics of natural sound features predict perceptual grouping. Computational and Systems Neuroscience (COSYNE) (2018). at <http://www.cosyne.org/c/index.php?title=Cosyne_18>
Lossy Compression of Uninformative Stimuli in the Auditory System. Association for Otolaryngology Mid-Winter Meeting (2017).
Learning Mid-Level Auditory Codes from Natural Sound Statistics. (2017).
MlynarskiMcDermott_Memo060.pdf (7.11 MB)
MlynarskiMcDermott_Memo060.pdf (7.11 MB) Adaptive Coding for Dynamic Sensory Inference. eLife (2018).
Learning Mid-Level Codes for Natural Sounds. Association for Otolaryngology Mid-Winter Meeting (2017).
Learning Mid-Level Auditory Codes from Natural Sound Statistics. Neural Computation 30, 631-669 (2018).
Lossy Compression of Sound Texture by the Human Auditory System. Society for Neuroscience Meeting (2016).
Learning mid-level codes for natural sounds. Computational and Systems Neuroscience (Cosyne) 2016 (2016). at <http://www.cosyne.org/c/index.php?title=Cosyne2016_posters_2> Wiktor_COSYNE_2015_hierarchy_final.pdf (2.52 MB)
Wiktor_COSYNE_2015_hierarchy_final.pdf (2.52 MB) Learning Mid-Level Codes for Natural Sounds. Advances and Perspectives in Auditory Neuroscience (2016). APAN_large_JHM kopia.pdf (19.74 MB)
APAN_large_JHM kopia.pdf (19.74 MB) A normalization model of visual search predicts single trial human fixations in an object search task. (2014). CBMM-Memo-008.pdf (854.51 KB)
CBMM-Memo-008.pdf (854.51 KB) There's Waldo! A Normalization Model of Visual Search Predicts Single-Trial Human Fixations in an Object Search Task. Cerebral Cortex 26(7), 26:3064-3082 (2016).
Function approximation by deep networks. Communications on Pure & Applied Analysis 19, 4085 - 4095 (2020). 1534-0392_2020_8_4085.pdf (514.57 KB)
1534-0392_2020_8_4085.pdf (514.57 KB) Deep vs. shallow networks: An approximation theory perspective. Analysis and Applications 14, 829 - 848 (2016).
An analysis of training and generalization errors in shallow and deep networks. (2018). CBMM-Memo-076.pdf (772.61 KB) CBMM-Memo-076v2.pdf (2.67 MB)
CBMM-Memo-076.pdf (772.61 KB) CBMM-Memo-076v2.pdf (2.67 MB) Deep vs. shallow networks : An approximation theory perspective. (2016). Original submission, visit the link above for the updated version (960.27 KB)
Original submission, visit the link above for the updated version (960.27 KB) An analysis of training and generalization errors in shallow and deep networks. Neural Networks 121, 229 - 241 (2020).
Learning Functions: When Is Deep Better Than Shallow. (2016). at <https://arxiv.org/pdf/1603.00988v4.pdf>
When and Why Are Deep Networks Better Than Shallow Ones?. AAAI-17: Thirty-First AAAI Conference on Artificial Intelligence (2017).
An analysis of training and generalization errors in shallow and deep networks. (2019). CBMM-Memo-098.pdf (687.36 KB) CBMM Memo 098 v4 (08/2019) (2.63 MB)
CBMM-Memo-098.pdf (687.36 KB) CBMM Memo 098 v4 (08/2019) (2.63 MB) NeuroDecodeR: A package for neural decoding analyses in R. bioRxiv (2022). at <https://www.biorxiv.org/content/10.1101/2022.12.17.520811v1>
Review of the CBMM workshop on the Turing++ Question: 'who is there?'. (2016). Review of the CBMM workshop on the Turing++ Question- 'who is there?' .pdf (555.71 KB)
Review of the CBMM workshop on the Turing++ Question- 'who is there?' .pdf (555.71 KB) NeuroDecodeR: a package for neural decoding in RData_Sheet_1.docx. Frontiers in Neuroinformatics 17, (2024).