Neural Networks With Tensor Flow
A neural network is a network or circuit of biological neurons, or, in a modern sense, an artificial neural network, composed of artificial neurons or nodes. Thus, a neural network is either a biological neural network, made up of biological neurons or an artificial neural network, used for solving artificial intelligence (AI) problems.
Below, I have included every assignment I completed for the following two courses:
- Introduction to TensorFlow for Artificial Intelligence, Machine Learning, and Deep Learning (4 weeks)
- Convolutional Neural Networks in TensorFlow (4 weeks)
What I learnt
First Week
Coded a neural network that learned the linear relationship between two variables.
Second Week
Implemented a callback that gives you more control over the training loop for your model.
Third Week
Implemented a convolutional neural network to assist you in the image classification task
Fourth Week
Implemented a CNN to assist you in the classification task for complex images.
Fifth Week
Implemented a convolutional neural network that classifies images of cats and dogs, along with the helper functions needed to pre-process the images.
Model achieved a max training accuracy of 98.54% and a max validation accuracy of a 82.7%.
Sixth Week
Implemented a convolutional neural network that classifies images of cats and dogs, along with the helper functions needed to pre-process the images!
Model achieved a max training accuracy of 78.69% and a max validation accuracy of a 82.56%.
Seventh Week
Implemented a convolutional neural network that leverages a pre-trained network to help you solve the problem of classifying humans from horses.
Model achieved a max training accuracy of 99.81% and a max validation accuracy of a 100%.
Eighth Week
Implemented a convolutional neural network that is able to perform multi-class classification tasks
Model achieved a max training accuracy of 89.23% and a max validation accuracy of a 94.63%.
