Kiprono Elijah Koech

Published in Towards Data Science

·Pinned

How Neural Network Works — with Worked Example (Neural Network Series) — Part 2

This article will build into the previous part of this series. We will cover Feed-Forward Neural Networks (FF-NN), focusing the discussion on computations done by NN. Previous part in the series: The Basics of Neural Networks (Neural Network Series) — Part 1 The Basics of Neural Networks (Neural Network Series) — Part 1 Neural Networkstowardsdatascience.com Neural Network Design (Recap) Neural Network is a system made up of…

Data Science

7 min read

How Neural Network Works — with Worked Example (Neural Network Series) — Part 2

Published in Towards Data Science

·Pinned

The Basics of Neural Networks (Neural Network Series) — Part 1

Neural Networks An Artificial Neural Network (ANN) or simply a Neural Network(NN) is interconnected layers of small units called nodes that perform mathematical operations to detect patterns in data. NN algorithms are built in a way that mimics how human neurons work (we will cover the connection between the two in the…

Artificial Intelligence

6 min read

The Basics of Neural Networks (Neural Network Series) — Part 1

Published in Towards Data Science

·Pinned

Cross-Entropy Loss Function

When working on a Machine Learning or a Deep Learning Problem, loss/cost functions are used to optimize the model during training. The objective is almost always to minimize the loss function. The lower the loss the better the model. Cross-Entropy loss is a most important cost function. It is used…

Data Science

6 min read

Published in Towards Data Science

·Pinned

Cross Validation in Machine Learning

Learn cross-validation process and why bootstrap sample has 63.2% of the original data — After training a machine learning model, every data scientist always want to know how well the trained model will perform on the unseen data. A good model is a model that performs well in, not only the training but also test data. To estimate the model performance, we often use…

Machine Learning

8 min read

Published in Towards Data Science

·Jun 9

How Neural Networks Actually Work — Python Implementation Part 2 (Simplified)

In this article, we continue to debunk the theory that Neural Network is a black box that we don’t quite understand how it works. We aim to implement Neural Nets in an easily understandable way. …

Data Science

7 min read

How Neural Networks Actually Work — Python Implementation Part 2 (Simplified)

Published in Towards Data Science

·May 26

How Neural Networks Actually Work — Python Implementation (Simplified)

Neural Network (NN) is a black box for so many people. We know that it works, but we don’t understand how it works. This article will demystify this belief by working on some examples to show how a neural network really works. …

Data Science

8 min read

How Neural Networks Actually Work — Python Implementation (Simplified)

Mar 9

Hierarchical Clustering — How it Actually Works

Clustering is an unsupervised machine learning technique for grouping data items that are similar. The process entails identifying natural groups in data. Customer segmentation and image processing and segmentation are two domains where clustering algorithms might be used. A segmented market allows for targeted advertising and general market research. …

Machine Learning

6 min read

Feb 4

…-taught data scientists study the trade-off between model interpretability and prediction accuracy. There are some cases where we prefer a less accurate or less flexible model because we are more interested in inference. To be honest, I did not focus on this topic during my self-study period.

Self-Taught Data Scientists Fail to Go Deep Enough

377

Soner Yıldırım

Well-taught piece.

Well-taught piece. I feel that every self-taught data scientist should conduct a very rational self-evaluation every time to discover the skills they still lack and fill up those loopholes. On the quoted text:- Isn't it gravious mistake to make an inference based on a less accurate model?

1 min read

Well-taught piece. I feel that every self-taught data scientist should conduct a very rational self-evaluation every time to discover the skills they still lack and fill up those loopholes.

On the quoted text:- Isn't it gravious mistake to make an inference based on a less accurate model?

Published in Towards Data Science

·Jan 4

Principal Component Analysis

Machine Learning (ML) modeling involves finding patterns in the data under consideration. In supervised learning, the model learns patterns through labeled data; that is, the data provided has the independent variables and the dependent variable. Based on the field, independent variables may have other names like explanatory, predictor, regressor, covariate…

Principal Component

10 min read

Dec 17, 2020

Regularization — A Technique Used to Prevent Over-fitting

The very essence of any machine learning project is to end up with a model that performs well on unseen data (test data). In some cases the model attains high accuracy on the training set but yield poor predictive performance in the test set — a case of over-fitting. In…

Data Science

8 min read

Regularization — A Technique Used to Prevent Over-fitting