AiAge - Artificial Intelligence AGe

Evaluating Object Detection Models Using Mean Average Precision - KDnuggets : In this article we will see see how precision and recall are used to calculate the Mean Average Precision (mAP).

Evaluating Deep Learning Models: The Confusion Matrix, Accuracy, Precision, and Recall - KDnuggets : This tutorial discusses the confusion matrix, and how the precision, recall and accuracy are calculated, and how they relate to evaluating deep learning models.

Working With The Lambda Layer in Keras - KDnuggets : In this tutorial we'll cover how to use the Lambda layer in Keras to build, save, and load models which perform custom operations on your data. Originally published at Paperspace: https://blog.paperspace.com/working-with-the-lambda-layer-in-keras

­­From Y=X to Building a Complete Artificial Neural Network - KDnuggets : In this tutorial, we will start with the most simple artificial neural network (ANN) and move to something much more complex. We begin by building a machine learning model with no parameters—which is Y=X.

Optimizing the Levenshtein Distance for Measuring Text Similarity - KDnuggets : For speeding up the calculation of the Levenshtein distance, this tutorial works on calculating using a vector rather than a matrix, which saves a lot of time. We’ll be coding in Java for this implementation.

A Guide to Preparing OpenCV for Android - KDnuggets : This tutorial guides Android developers in preparing the popular library OpenCV for use. Using a step-by-step guide, the library will be imported into Android Studio and then can be used for performing any of the operations it supports, such as object detection, segmentation, tracking, and more.

Introduction to Federated Learning - KDnuggets : Federated learning means enabling on-device training, model personalization, and more. Read more about it in this article.

Breaking Privacy in Federated Learning - KDnuggets : Despite the benefits of federated learning, there are still ways of breaching a user’s privacy, even without sharing private data. In this article, we’ll review some research papers that discuss how federated learning includes this vulnerability.

CoinTex is an open-source cross-platform multi-level adventure game developed in Python using Kivy. CoinTex is available for Android at Google Play: https://play.google.com/store/apps/details?id=coin.tex.cointexreactfast&hl=en To pass a level in CoinTex, the player has to collect all the randomly distributed coins while avoiding collision with the monsters and the fires. The monsters are moved randomly. Using only the genetic algorithm (GA) without any machine/deep learning algorithms, a game playing agent is created that plays CoinTex like a professional. The agent is able to stand even in complex levels with many coins, monsters, and fires. The GA is implemented using a Python 3 library named PyGAD. Find its documentation here to get started: https://pygad.readthedocs.io . Install PyGAD using pip: pip install pygad The source code of CoinTex at GitHub: https://github.com/ahmedfgad/CoinTex The source code of the genetic algorithm agent: https://github.com/ahmedfgad/CoinTe...

My profile at KDnuggets.com Ahmed Gad

This tutorial discusses how to use the genetic algorithm (GA) for reducing the feature vector extracted from the Fruits360 dataset in Python mainly using NumPy and Sklearn. Feature Reduction using Genetic Algorithm with Python

This tutorial discusses how to use the genetic algorithm (GA) for reducing the feature vector extracted from the Fruits360 dataset in Python mainly using NumPy and Sklearn. Feature Reduction using Genetic Algorithm with Python

This tutorial explains the usage of the genetic algorithm for optimizing the network weights of an Artificial Neural Network for improved performance. Artificial Neural Networks Optimization using Genetic Algorithm with Python

Artificial Neural Networks Optimization using Genetic Algorithm with Python - Towards Data Science In a previous tutorial titled “ Artificial Neural Network Implementation using NumPy and Classification of the Fruits360 Image Dataset ” available in my LinkedIn profile at this  link , an artificial neural network (ANN) is created for classifying 4 classes of the Fruits360 image dataset. The source code used in this tutorial is available in my  GitHub page . This tutorial is also available at TowardsDataScience  here . A quick summary of this tutorial is extracting the feature vector (360 bins hue channel histogram) and reducing it to just 102 element by using a filter-based technique using the standard deviation. Later, the ANN is built from scratch using NumPy. The ANN was not completely created as just the forward pass was made ready but there is no backward pass for updating the network weights. This is why the accuracy is very low and not exceeds 4...

This tutorial builds artificial neural network in Python using NumPy from scratch in order to do an image classification application for the Fruits360 dataset Artificial Neural Network Implementation using NumPy and Image Classification

Building Surveillance System Using USB Camera and Wireless-Connected Raspberry Pi

Building an Image Classifier Running on Raspberry Pi

Derivation of Convolutional Neural Network from Fully Connected Network Step-By-Step In image analysis, #convolutional neural networks (#CNNs or #ConvNets for short) are time and memory efficient than fully connected (#FC) networks. But why? What are the advantages of ConvNets over FC networks in image analysis? How is #ConvNet derived from FC networks? Where the term #convolution in CNNs came from? These questions are to be answered in this #article. #FullyConnected #CNN #DeepLearning #DL #MachineLearning #ML #ANN #NeuralNetwork #NN #DataAnalysis #DataScience #KDnuggets Article @ #LinkedIn https://www.linkedin.com/pulse/derivation-convolutional-neural-network-from-fully-connected-gad/ Article @ #SlideShare https://www.slideshare.net/AhmedGadFCIT/derivation-of-convolutional-neural-network-convnet-from-fully-connected-network