DataSphere

While designing a Neural Network, we can use Dataset & Data Loader for efficient memory management. Think of them as a backbone for providing data to a machine learning model. Optuna package available in the PyTorch library will be used to calculate the hyper parameters. Agenda of this blog : How we are making the model memory efficient by using Dataset, Data Loader How to use Optuna package to select accurate Hyper Parameters Hyper parameters in a Neural Network : Learning rate Batch size No. of epochs Drop out ratio No. of hidden layers No. of hidden units Normalization - Batch norm etc. Optimizers - Adam, Momentum, NAG, RMS Prop etc. Generally, we manually try above hyper parameters with different reasonable values and try testing a model and finalize the accurate paramters which are best suitable for our model. But manual way takes time as we need to see different possibilities by using different values for these parameters and then come up with correct parameters and values....

Lets understand how to identify the type of flower based on the given input data using Neural Networks. Below are the 3 types of flowers named as: iris setosa iris versicolor iris virginica and each flower have a different area called as petal and sepal, our ML need to predict the flower type based on this data if we provide an unseen data to our ML model once training is done(during testing phase). Feature values that we are considering were : Petal length  Petal width Sepal length  Sepal width Problem statement :                        Based on above features, ML model should predict whether the given data belongs to any one of above flower. Before digging into building/programming above neural network we need to understand about one of the important python library called sklearn .   Scikit-learn  :   Scikit-learn is one of the famous machine learning libraries in Python. It is build for Machine ...

After discussing about the fundamentals of Neural Networks and Deep Learning, we have arrived to an exciting stage where we can learn how we program a Neural Network.  I have created some simple programs to get some basic idea on how to program a Neural Network and I have used a Python library called PyTorch to program it. Program 1 : Calculate total numbers of parameters in a neural network Points to remember : We need to import nn submodule from main module torch We need to inherit the Module class available in torch.nn submodule We should use self otherwise method doesn't get class objects data Do not confuse about forward(), we don't call it directly, it will be called via constructor in super class. Hence using self. p.numel() return the elements in the Model. Please see my explanation in the downloaded code Need basics of Oops concepts in Python # importing modules torch, nn(neural network): nn is a sub module in main module torch import torch import torch.nn as nn...

We are going to discuss about Normalization & Optimizers which will be used across AI, we will use them in LLM's, Agentic AI framework etc.  As we discussed in our previous blogs(links for previous blogs are mentioned at the end of this blog), while calculating gradients, when the previous weights are almost similar to new weights, we will land into a problem called Vanishing Gradient . Similarly when current weight is too large than the previous weights, then we will land into Exploding Gradient issue.  Using  Normalization problem we are going to prevent Vanishing & Exploding Gradient problems.  This blogs agenda : Normalization Batch Normalization (Useful in Neural Network) Layer Normalization (Useful in LLM's) Weights Initialization Xavier He EWMA (Exponential Weighted Moving Average) We will use it in Optimizers  like Momentum, NAG, Adagrad, RMSProp, Adam Normalization           Normalization in Neural Networks and De...