Articles

colin working on a remote jupyter notebook

Remote jupyter notebooks with ssh port forwarding

Access your jupyter notebook server remotely

Read More →

steaven seagal rotten tomato

Word Embedding and Sentiment Analysis (IMDB)

Word embedding is essential in natural language processing with deep learning. This technique allows the network to learn about the meaning of the words. In this post, we classify movie reviews in the IMDB dataset as positive or negative, and provide a visual illustration of embedding.

Read More →

word encoding for natural language processing

Text Preprocessing For Machine Learning (yelp dataset part 2)

The yelp dataset is large, and it's in text format. Here are detailed explanations and all the code needed to convert it to a numpy array for machine learning.

Read More →

panda

Simple Text Mining with Pandas

Prepare the yelp dataset (shop reviews) for natural language processing.

Read More →

garbage in, garbage out in a neural network

Overfitting Illustrated

One of the most important issues in machine learning, illustrated in a small 2D classification problem.

Read More →

non-linear classification problem

Logistic Regression vs Neural Network: Non Linearities

What are non-linearities and how hidden neural network layers handle them.

Read More →

convolutional layer

Tuning a Deep Convolutional Network for Image Recognition, with keras and TensorFlow

You would like to try deep learning but don't have a GPU? Or you don't want to install software on your computer? This tutorial is for you, as it requires no specific hardware or software.

Read More →

neural network with a single neuron

The 1-Neuron Network: Logistic Regression

The most simple neural network. Learn how a neuron is working.

Read More →

anaconda logo

Install Anaconda for Machine Learning and Data Science in Python

General instructions to install Anaconda, which is used in most posts on this blog.

Read More →

Tags: python
artist view of a neural network

First Neural Network with Keras

Keras is easy and powerful. Give it a try by training your first neural net to classify handwritten digits.

Read More →

-->