Go to the profile of  Paras Patidar
Paras Patidar
I am working on Machine Learning, Python and Django.
2 min read

Terms to remember while building a Machine Learning Model

There are different terms we should remember while training our machine learning model, so that we can use our machine learning model more effectively and properly.

Terms to remember while building a Machine Learning Model

There are different terms we should remember while training our machine learning model, so that we can use our machine learning model more effectively and properly.

I will be using a code example from the Udacity to explain you the concept.

udacity.com

model = tf.keras.Sequential([
    tf.keras.layers.Dense(units=1,input_shape=[1])
])
model.compile(loss='mean_squared_error',optimizer=tf.keras.optimizers.Adam(0.1))
history = model.fit(C,F,epochs=500,verbose=False)
model.predict([100.0])

Terms to Remember :

  • Feature - The inputs to our model
  • Examples - An input/output pair used for training
  • Labels - The output of the model
  • Layer - A collection of nodes connected together within a neural network
  • Model - The representation of your neural network
  • Dense and Fully Connected(FC) - Each node in one layer is connected to each node in the previous layer
  • Weights and biases - The internal variables of the model
  • Loss - The discrepancy(difference) between the desired ouput and the actual output.
  • MSE - Mean Squared Error,  Mean squared error, a type of loss function that counts a small number of large discrepancies as worse than a large number of small ones.
  • Gradient Descent - An algorithm that changes the internal variables a bit at a time to gradually reduce the loss function
  • Optimizer - A specific implementation of the gradient descent algorithm.
  • Learning rate: The “step size” for loss improvement during gradient descent.
  • Batch: The set of examples used during training of the neural network
  • Epoch: A full pass over the entire training dataset
  • Forward pass: The computation of output values from input
udacity.com
  • Backward pass (backpropagation): The calculation of internal variable adjustments according to the optimizer algorithm, starting from the output layer and working back through each layer to the input.
udacity.com

Source : Udacity

Posts To Read :

Model Evaluation and Bias-Variance Trade-Off In Machine Learning

What is Deep Learning ?

What is Machine Learning ?

Thank You !