To predict the species of penguin, being learned from the training dataset, this model,
/penguin-classifier.h5, predicts if a particular penguine is Gentoo, Adelie, Chinstrap. The dataset used in the this project is a subset of data collected and made available by Dr. Kristen Gorman and the Palmer Station, Antarctica LTER, a member of the Long Term Ecological Research Network.
The penguins dataset used in the this project is a subset of data collected and made available by Dr. Kristen Gorman and the Palmer Station, Antarctica LTER, a member of the Long Term Ecological Research Network. The Species column is the label our model will predict. Each label value represents a class of penguin species, encoded as 0, 1, or 2. The following code shows the actual species to which these class labels corrrespond.
In reality, I can solve the penguin classification problem easily using classical machine learning techniques without the need for a deep learning model; but it's a useful, easy to understand dataset.
The contructed neural network has following features:
- An input layer that receives an input value for each feature (in this case, the four penguin measurements) and applies a ReLU activation function.
- A hidden layer that receives ten inputs and applies a ReLU activation function.
- An output layer that uses a SoftMax activation function to generate an output for each penguin species (which represent the classification probabilities for each of the three possible penguin species). Softmax functions produce a vector with probability values that sum to 1.
The plot of loss distribution is
Dr. Kristen Gorman
Palmer Station, Antarctica LTER
Long Term Ecological Research Network