New Results
Reverse engineering neural networks to characterise their cost functions
View ORCID ProfileTakuya Isomura, View ORCID ProfileKarl Friston
doi: https://doi.org/10.1101/654467
Takuya Isomura
1Laboratory for Neural Computation and Adaptation, RIKEN Center for Brain Science, Wako, Saitama 351-0198, Japan
Karl Friston
2Wellcome Centre for Human Neuroimaging, Institute of Neurology, University College London, 12 Queen Square, London, WC1N 3AR, UK
Article usage
Posted May 31, 2019.
Reverse engineering neural networks to characterise their cost functions
Takuya Isomura, Karl Friston
bioRxiv 654467; doi: https://doi.org/10.1101/654467
Subject Area
Subject Areas
- Biochemistry (11736)
- Bioengineering (8749)
- Bioinformatics (29186)
- Biophysics (14964)
- Cancer Biology (12086)
- Cell Biology (17403)
- Clinical Trials (138)
- Developmental Biology (9418)
- Ecology (14176)
- Epidemiology (2067)
- Evolutionary Biology (18299)
- Genetics (12235)
- Genomics (16795)
- Immunology (11863)
- Microbiology (28066)
- Molecular Biology (11582)
- Neuroscience (60936)
- Paleontology (451)
- Pathology (1870)
- Pharmacology and Toxicology (3238)
- Physiology (4956)
- Plant Biology (10423)
- Synthetic Biology (2883)
- Systems Biology (7338)
- Zoology (1650)