A large deep learning model can take a long time to train. You lose a lot of work if the training process interrupted in the middle. But sometimes, you actually want to interrupt the training process in the middle because you know going any further would not give you a better model. In this post, […]
You can learn a lot about neural networks and deep learning models by observing their performance over time during training. For example, if you see the training accuracy went worse with training epochs, you know you have issue with the optimization. Probably your learning rate is too fast. In this post, you will discover how […]
When you build and train a PyTorch deep learning model, you can provide the training data in several different ways. Ultimately, a PyTorch model works like a function that takes a PyTorch tensor and returns you another tensor. You have a lot of freedom in how to get the input tensors. Probably the easiest is […]
Training a neural network or large deep learning model is a difficult optimization task. The classical algorithm to train neural networks is called stochastic gradient descent. It has been well established that you can achieve increased performance and faster training on some problems by using a learning rate that changes during training. In this post, […]
Dropout is a simple and powerful regularization technique for neural networks and deep learning models. In this post, you will discover the Dropout regularization technique and how to apply it to your models in PyTorch models. After reading this post, you will know: How the Dropout regularization technique works How to use Dropout on your […]
The loss metric is very important for neural networks. As all machine learning models are one optimization problem or another, the loss is the objective function to minimize. In neural networks, the optimization is done with gradient descent and backpropagation. But what are loss functions, and how are they affecting your neural networks? In this […]
A deep learning model in its simplest form are layers of perceptrons connected in tandem. Without any activation functions, they are just matrix multiplications with limited power, regardless how many of them. Activation is the magic why neural network can be an approximation to a wide variety of non-linear function. In PyTorch, there are many […]
A deep learning model is a mathematical abstraction of data, in which a lot of parameters are involved. Training these parameters can take hours, days, and even weeks but afterward, you can make use of the result to apply on new data. This is called inference in machine learning. It is important to know how […]
The “weights” of a neural network is referred as “parameters” in PyTorch code and it is fine-tuned by optimizer during training. On the contrary, hyperparameters are the parameters of a neural network that is fixed by design and not tuned by training. Examples are the number of hidden layers and the choice of activation functions. […]
The most popular deep learning libraries in Python for research and development are TensorFlow/Keras and PyTorch, due to their simplicity. The scikit-learn library, however, is the most popular library for general machine learning in Python. In this post, you will discover how to use deep learning models from PyTorch with the scikit-learn library in Python. […]
