• Understanding Pytorch Tensors

    import torch Creating a tensor in PyTorch a = torch.tensor([1, 2, 3, 4]) a tensor([1, 2, 3, 4]) Checking the tensor type a.type() 'torch.LongTensor' Type of data stored in the tensor a.dtype torch.int64 Create a tensor of specific type b = torch.FloatTensor([1, 2, 3, 4]) b.type() 'torch.FloatTensor' Size and dimension...

  • Hyperparameter Tuning in Deep Neural Networks

    One way to make your deep learning model more accurate and generate better results is to tune your model’s hyperparameters. By doing so, you can speed up your training process and optimize the outputs provided by the model. In this post, we try to figure out some ways to make...

  • Optimization Algorithms in Deep Learning

    Building deep neural networks is one thing, but optimizing it to train faster with better accuracy is a completely different set of domain. So, it is very important that we focus on optimizing our algorithms to converge faster with desirable accuracy and details. In this post, we discuss about a...

  • Practical Aspects of Deep Learning - 2

    Welcome to the second part of “Practical Aspects of Deep Learning”. If you haven’t already gone through the first part, then you can read the post here. In this post, we will be discussing on how to prevent the model from diverging from a good solution and also efficient processes...

  • Practical Aspects of Deep Learning - 1

    Deep Learning is a subset of Machine Learning which has come to evolve highly in the past few years. It involves neural networks with the number of hidden layers greater than one, hence the term “deep”. The basis of a neural network in deep learning is Logistic Regression and one...