|
gptkbp:instance_of
|
gptkb:academic_journals
|
|
gptkbp:addresses
|
image processing
|
|
gptkbp:analyzes
|
training algorithms
|
|
gptkbp:applies_to
|
gradient descent
|
|
gptkbp:author
|
gptkb:Yann_Le_Cun
|
|
gptkbp:collaboration
|
multiple authors
|
|
gptkbp:contains
|
mathematical models
|
|
gptkbp:contributes_to
|
gptkb:machine_learning
|
|
gptkbp:discusses
|
feature extraction
|
|
gptkbp:explores
|
convolutional networks
|
|
gptkbp:focuses_on
|
document recognition
|
|
gptkbp:has_implications_for
|
AI development
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
Gradient-Based Learning Applied to Document Recognition
|
|
gptkbp:includes
|
gptkb:experimental_results
|
|
gptkbp:influences
|
computer vision
|
|
gptkbp:involves
|
data preprocessing
|
|
gptkbp:is_associated_with
|
Yann Le Cun's research
|
|
gptkbp:is_available_in
|
academic databases
|
|
gptkbp:is_cited_in
|
over 500 times
machine learning textbooks
|
|
gptkbp:is_compared_to
|
traditional methods
|
|
gptkbp:is_discussed_in
|
gptkb:academic_conferences
|
|
gptkbp:is_evaluated_by
|
peer review
|
|
gptkbp:is_influenced_by
|
statistical learning theory
|
|
gptkbp:is_part_of
|
computer science curriculum
machine learning literature
|
|
gptkbp:is_recognized_as
|
seminal work
|
|
gptkbp:is_recommended_by
|
future research directions
|
|
gptkbp:is_referenced_in
|
numerous subsequent studies
|
|
gptkbp:is_related_to
|
pattern recognition
|
|
gptkbp:is_supported_by
|
empirical evidence
|
|
gptkbp:is_used_in
|
automated systems
|
|
gptkbp:presents
|
case studies
|
|
gptkbp:provides
|
theoretical foundations
|
|
gptkbp:published_by
|
gptkb:IEEE
|
|
gptkbp:published_in
|
gptkb:IEEE_Transactions_on_Pattern_Analysis_and_Machine_Intelligence
|
|
gptkbp:reviews
|
literature on document recognition
|
|
gptkbp:uses
|
gptkb:neural_networks
|
|
gptkbp:utilizes
|
backpropagation
|
|
gptkbp:was_a_demonstration_of
|
high accuracy
|
|
gptkbp:written_in
|
English
|
|
gptkbp:year
|
gptkb:1998
|
|
gptkbp:bfsParent
|
gptkb:Yann_Le_Cun
|
|
gptkbp:bfsLayer
|
3
|