Machine Learning

Input LayerThe input layer is the layer that contains the inputs we want to feed into our algorithm, also known as a model. Our algorithm will do some calculations using our inputs and then spit out an answer.The input layer is usually represented as a vector of numbers. For our image example, how do we turn an image into a vector of numbers? Since the image is just a matrix of … [Read more...] about Mathematics You Should Know To Understand Neural Networks

Photo by Rich Smith on UnsplashWith the rise of machine learning MOOCs and cheaper compute power, it’s becoming much easier for data enthusiasts to explore the depths of machine learning and the data science toolkit. Sprinkle in the continuous success stories surrounding machine learning in popular news, and data laymen begin to have an appetite for data science. Before I go on … [Read more...] about Stop Using The Machine Learning Easy Button

The above plot shows an example on the EURUSD hourly data plotted with the Equilibrium Indicator in blue. The full code can be find below:def ema(Data, alpha, lookback, what, where): # alpha is the smoothing factor# window is the lookback period# what is the column that needs to have its average calculated# where is where to put the exponential moving averagealpha = alpha / … [Read more...] about The Equilibrium Indicator —  Profiting from Mean-Reversion.

This is the pseudocode for the algorithm that we just talked about above:So let's start coding! The entire code, ready to run, will be at the end of this article by the way :)To start our DQN, we need to start with the network itself that will approximate the q value of the action-value function. I'm going to hope that you read that gym documentation from earlier and that this … [Read more...] about Reinforcement Learning: DQN w Pytorch

Arabic NLP tutorial on creating Arabic Sentence Embeddings with Multi-Task Learning for fast and efficient Semantic Textual Similarity tasks.Photo by TOMOKO UJI on UnsplashIn the first article of this Arabic natural language processing (NLP) series, I introduced a transformer language model named AraBERT (Arabic Bidirectional Encoder Representations from Transformers) released … [Read more...] about Arabic Sentence Embeddings with Multi-Task Learning

In this article I will be covering the basics of TensorFlow that you need to understand before going deep into TensorFlow. The topics include what is a tensor, constant and variable.TensorFlow is an open-source library for machine learning developed by Google. TensorFlow consist of both High-level API and Low level API .High-level API provides more functionality within one … [Read more...] about Introduction to TensorFlow

Class Imbalance is a classic problem one may face while working on a ml problem, in such case, each class is not equally represented by the number of data points.Imbalance LearningThe objective of imbalance learning can be generally described as obtaining a classifier that will provide high accuracy for the minority class without severely jeopardizing the accuracy of the … [Read more...] about A Deep Dive into Class Imbalance

First published at L’Atelier PNB Paribas on March 4, 2021As a black woman past the age of 40, I knew I was highly susceptible to biases built into this software, even as a member of a triple-protected class with a background in law, computer technology, and intellectual property. The company’s aggressive push towards its AI software prompted my loss of interest in the job, and … [Read more...] about Managed Out by Anti-Bias Tools: The Selective Service of Recruitment AI

Naive Bayes algoritması, sınıflandırma işlemlerinde kullanılan olasılık esaslı bir makine öğrenme modelidir. Algortima olasılıkları hesaplar ve olasılığı yüksek olan duruma göre sınıflandırmaları gerçekleştirir. Bu sınıflandırma modeli Bayes teoremine dayanır.Bayes TeoremiBu teorem bir sonucun sebebini bulurken sonucun hangi olasılıkla hangi sebepten kaynaklandığını bulmaya … [Read more...] about Naive Baves Sınıflandırıcısı -Machine Learning

After the rise of AI, many companies begun to capture people’s online behavior, and strive to label everyone with interest and temper, and gradually improve as people’s online behavior change. After labeling people, they also recognize people’s mindset. AI will give people accurate push, verify people’s interest in news, shopping information, fitness information and make AI … [Read more...] about How the artificial intelligence and its subfields simulate the consumer mind