# Computer Vision: How to Set Up Your CNN Architecture

## Learn how to design the architecture for your next computer vision project and view example code in PyTorch

While creating a new computer vision project, there are a lot of decisions you have to make that’ll ultimately affect the resulting performance of your model. You can choose between different types of layers, such as the convolutional layer, pooling layer, fully connected layer, softmax layer, and dropout layer. In addition, it’s quite common to have multiple layers of the same type.

Further, most of the different types of layers can be customized, and you’ll usually have to set the number of input and output nodes — as well as other parameters. …

# How to Create a Simple Neural Network in Python

## Learn how to create a neural network and teach it to classify vectors

Machine learning has had a huge impact on the world over the last few decades, and its popularity seems to be ever-growing. Recently, more and more people have familiarised themselves with machine learning subfields, like neural networks, which are networks inspired by the human brain. In this article, Python code for a simple neural network that classifies 1x3 vectors with 10 as the first element, will be presented.

# Step 1: Import NumPy, Scikit-learn and Matplotlib

`import numpy as npfrom sklearn.preprocessing import MinMaxScalerimport matplotlib.pyplot as plt`

We will be using three packages for this project. NumPy will be used for creating vectors and matrices, as well as mathematical operations. Scikit-learn will be used for scaling the data, and Matplotlib will be used for plotting the error development during the training of the neural network. …

# What is an Activation Function in a Neural Network?

## Learn what an activation function is, why you need it, and how to choose the best activation function for your machine learning project

Neural network algorithms learn from data. This happens through training, which usually includes multiple iterations of forward and backward pass. A forward pass is done to predict the output based on the given input data, while a backward pass is used to minimize an error function and make the algorithm predict better during the next iteration.

# A Concise Description of GPT-3

## GPT-3 is a text predictor that can be used to create articles and books, design websites, and do arithmetic

GPT-3 is a new tool, based on a machine-learning algorithm, which is used to predict text. It is released by OpenAI, where Elon Musk and Sam Altman are two of the founders, and both of them have been outspoken about the possibility of artificial general intelligence (AGI), as well as the opportunities and dangers that it may present our society with. Therefore, they wanted to create a company that is developing artificial intelligence in a responsible manner. …

# Should you Use a GPU for Your Machine Learning Project?

## Learn the main differences between using CPU and GPU for your machine learning project, and understand which to choose

Many machine learning projects involve training an algorithm on massive amounts of data, and hence requires a lot of computing power. This computing power is typically tied to the number and quality of the processing units, such as the central processing unit (CPU) or the graphics processing unit (GPU). The performance can also be greatly affected by the number of cores in the processing units. A core is a unit that can perform computing operations, and the more cores a CPU or GPU has, the more operations it can run in parallel. …

# 3 Startup Ideas you Can Start Today

## 1. Wash and dry dishes in one movement

Washing the dishes takes up a lot of time, makes your hands greasy, and does not always yield a perfect result. For most of today’s dishwashers to work, you will have to clean up the dishes before putting them into the dishwasher. Then the dishwasher will spend multiple hours washing the dishes before you pick them out and place them in your dish cabinet.

To solve these problems, a startup should build a dishwasher that washes the dishes instantly. Think about automatic car wash machines where you drive your car into a garage, water and soap are applied, multiple brushes make the car clean, and then finally the car is dried before you can drive out of the garage. Now, imagine a similar solution for dishes. You place a plate into something that looks a lot like a slot toaster, and then 5 seconds later the plate pops up clean and dry, and can be placed into the dish cabinet right away. …

# What Is the Difference Between a Tensor, a Matrix, and a Vector?

## Read this short guide for a description of the difference between a tensor, matrix, and vector

Algebra is an important element of mathematics and has a lot of practical applications. Among other things, it plays a crucial role in the economy, quantum computing, and machine learning. For the latter one, matrices and vectors are important, while the popular Python framework PyTorch uses tensor-based operations. Despite their similarities, a tensor is neither a matrix nor a vector, contrary to what many people think.

A matrix is a grid of m x n numbers surrounded by square brackets. Here, m is the number of rows and n is the number of columns. Mathematical operations can be performed on matrices, such as e.g. …

# How to Find an Interesting Idea for Your Next Machine Learning Project

## A three-step process to increase the amount and quality of ideas for your next side project

I have wanted to learn machine learning for quite some time now. As many people do when they want to learn something new I did multiple courses, scrolled through Youtube for explanatory videos, and read about different elements of machine learning on the internet. Although all of that gave me a great overview and a basic understanding of what machine learning is, I realized that I didn’t acquire the skills necessary to make something useful by myself.

I needed to get hands-on experience with relevant projects to make the newly acquired knowledge useful. I could have tried to do a competition on Kaggle or found a clean dataset to work with, but I didn’t want to do something someone else had done before. I believe that you learn most when you try to challenge yourself to accomplish something no one else has done. …

# Startups Should Be Built on Secrets

## Finding secrets instead of problems often result in better ideas

Legendary entrepreneur and VC Peter Thiel has for a long time been advocating big, revolutionary ideas. In his book, Zero to One, he introduces the concept of secrets. Secrets are described as non-obvious problems and should be the basis for startups, according to Thiel. For a short summary of Zero to One, including the most important takeaways, see the article below.

Secrets are often divided into two groups:

1. Secrets about people
2. Secrets of nature

People secrets are unknown characteristics about people. These are often unknown either because the person isn’t able to see the secret or because he or she is trying to hide it from others. Due to the non-obvious nature of people secrets, the best place to look for them is where no one else is looking. All people have different backgrounds and knowledge, and will most often think in terms of what they know. There are, however, many fields that matter, but haven’t been standardized yet. One such field is nutrition, which is important to all people, but very few people study. …

# How to Generate Great Ideas

Idea generation is crucial for most businesses and can be perceived as difficult if you don’t have the right mindset. I once met the founder of Sonos and software.com, John MacFarlane, and he claimed that he saw about 20 product ideas in every room he entered. Many of the best entrepreneurs in the world have a similar mind for ideas, both when it comes to startup ideas, feature ideas, project ideas and all other idea types. In this article, regular people will be taught how to change their mindset to generate the same amount of high quality ideas.

When trying to come up with new ideas there are really two phases you go…