Neural Network Optimization
This article is the third in a series of articles aimed at demystifying neural networks and outlining how to design and implement them. In this article, I will discuss the following concepts related to the optimization of neural networks: Challenges with optimization Momentum Adaptive Learning Rates Parameter Initialization Batch... Read more
Intermediate Topics in Neural Networks
This article is the second in a series of articles aimed at demystifying the theory behind neural networks and how to design and implement them for solving practical problems. In this article, I will cover the design and optimization aspects of neural networks in detail. The topics in this... Read more
Keras Metrics: Everything You Need To Know
Keras metrics are functions that are used to evaluate the performance of your deep learning model. Choosing a good metric for your problem is usually a difficult task. you need to understand which metrics are already available in Keras and tf.keras and how to use them, in many situations you need... Read more
Simple Guide to Hyperparameter Tuning in Neural Networks
A step-by-step Jupyter notebook walkthrough on hyperparameter optimization. This is the fourth article in my series on fully connected (vanilla) neural networks. In this article, we will be optimizing a neural network and performing hyperparameter tuning in order to obtain a high-performing model on the Beale function—one of many test... Read more
Deep Q-Learning Algorithm in Reinforcement Learning
In this article, we will discuss Q-learning in conjunction with neural networks (NNs). This combination has the name deep Q-network (DQN). This article is an excerpt from the book Deep Reinforcement Learning Hands-on, Second Edition by Max Lapan. This book provides you with an introduction to the fundamentals of RL,... Read more
Building a Convolutional Neural Network: Male vs Female
In this blog, we are going to classify images using Convolutional Neural Network (CNN), and for deployment, you can use Colab, Kaggle, or even use your local machine since the dataset size is not very large. At the end of this, you will be able to build your own... Read more
Adversarial Attacks on Deep Neural Networks
Our deep neural networks are powerful machines, but what we don’t understand can hurt us. As sophisticated as they are, they’re highly vulnerable to small attacks that can radically change their outputs. As we go deeper into the capabilities of our networks, we must examine how these networks really... Read more
Building Neural Networks with Perceptron, One Year Later — Part III
Inside Perceptron Each neuron in a neural network like Perceptron will, at some point, have a value. Each weight (the neuron links) will also have a value, all of which the user sets initially as random decimals between a specified range. This is the third part in a three-part... Read more
Classic Regularization Techniques in Neural Networks
Neural networks are notoriously tricky to optimize. There isn’t a way to compute a global optimum for weight parameters, so we’re left fishing around in the dark for acceptable solutions while trying to ensure we don’t overfit the data. This is a quick overview of the most popular model regularization... Read more
5 Essential Neural Network Algorithms
Data scientists use many different algorithms to train neural networks, and there are many variations of each. In this article, I will outline five algorithms that will give you a rounded understanding of how neural networks operate. I will start with an overview of how a neural network works,... Read more