Evolution of neural network|Machine Learning| SNS institutions

#snsinstitutions #snsdesignthinkers #designthinking in this video describes about
Hebbian learning deals with neural plasticity.
 Hebbian learning is unsupervised and deals with long-term potentiation.

 Hebbian learning deals with pattern recognition and exclusive-or circuits deal with if-
then rules.

 Backpropagation solved the exclusive-or issue that Hebbian learning could not
handle.
 This also allowed for multi-layer networks to be feasible and efficient.
 If an error was found, the error was solved at each layer by modifying the weights at
each node.
This led to the development of support vector machines, linear classifiers, and max-
pooling. The vanishing gradient problem affects feedforward networks that use back

propagation and recurrent neural network.
 This is known as deep-learning.
 Hardware-based designs are used for biophysical simulation and neurotrophic
computing. They have large scale component analysis and convolution creates new
class of neural computing with analog.
 This also solved back-propagation for many-layered feedforward neural networks.
Convolutional networks are used for alternating between convolutional layers and
max-pooling layers with connected layers (fully or sparsely connected) with a final
classification layer.
 The learning is done without unsupervised pre-training. Each filter is equivalent to a
weights vector that has to be trained.
 The shift variance has to be guaranteed to dealing with small and large neural
networks. This is being resolved in Development Networks.

 Some of the other learning techniques involve error-correction learning, memory-
based learning and competitive learning.

Видео Evolution of neural network|Machine Learning| SNS institutions канала S.Saranya SNS