A collection of attempted advice for training neural nets with a focus on how to structure that process over time:
Link
#artificialintelligence #neuralnetwork
@pythonicAI
Link
#artificialintelligence #neuralnetwork
@pythonicAI
karpathy.github.io
A Recipe for Training Neural Networks
Musings of a Computer Scientist.
Bi-tempered logistic loss for training neural networks with noisy data
Link
#neuralnetwork #artificialintelligence
@pythonicAI
Link
#neuralnetwork #artificialintelligence
@pythonicAI
Googleblog
Bi-Tempered Logistic Loss for Training Neural Nets with Noisy Data
Useful paper about calibration of NN to reduce overfit
https://arxiv.org/pdf/1706.04599.pdf
#paper #neuralnetwork #artificialintelligence
@pythonicAI
https://arxiv.org/pdf/1706.04599.pdf
#paper #neuralnetwork #artificialintelligence
@pythonicAI
Can you classify two class circle data using neural network with only two neurons?
https://arxiv.org/abs/1901.00109
#paper #neuralnetwork #artificialintelligence
@pythonicAI
https://arxiv.org/abs/1901.00109
#paper #neuralnetwork #artificialintelligence
@pythonicAI
The key idea behind the Convolutional Neural Nets:
The ability of learning networks can be greatly enhanced by providing constraints from the task domain.
Link
#deeplearning #convolution #neuralnetwork #machinelearning #article
@pythonicAi
The ability of learning networks can be greatly enhanced by providing constraints from the task domain.
Link
#deeplearning #convolution #neuralnetwork #machinelearning #article
@pythonicAi