In the past few years, artificial neural networks evolved to reach a human-like performance in tasks such object recognition, speech and audio analysis, natural language processing and much more. This short master's degree presentation discuss some approaches. The complementary paper can be found in http://hiveorama.com/papers/DeepLearning-NelsonForte.pdf.
9. Performance ILSVRC2013
Team Comments Error rate
Clarifai
Average of multiple models on original
training data.
0.11743
Clarifai
Another attempt at multiple models on
original training data.
0.1215
Clarifai Single model trained on original data. 0.12535
NUS
adaptive non-parametric rectification of
all outputs from CNNs and refined
PASCAL VOC12 winning solution, with
further retraining on the validation set.
0.12953
NUS
adaptive non-parametric rectification of
all outputs from CNNs and refined
PASCAL VOC12 winning solution.
0.13303
[4]
14. References
1. Wong, Rachel et al. (2005): "Circuits of vertebrate retina". Nature
Magazine, Volume 9 Number 1.
2. Huang G.B., Lee H., Miller E. L. (2012): “Learning Hierarchical
Representations for Face Verification with Convolutional Deep Belief
Networks”
3. Ng A. et al (2012): “Emergence of Object-Selective Features in
Unsupervised Feature Learning.”
4. Image-net.org, (2014). ImageNet. Available at: http://www.image-net.org/.
Editor's Notes
Invariance theory: Objects are recognized by structural information or individual parts. Rotation and completion are made by invariant brain models.
Especialização das células
Células horizontais -> Reconhecer formas difusas
Células bipolares -> Contraste e luz
Células amácrinas -> Resolução (ajuste de foco)
Células ganglionares -> Separação e caracteríticas