Tutorials

There are several tutorials for both machine learning and deep learning. Each tutorial consists of either a walkthrough a topic or a code demo.

Pic

Programming and Mathematics Tutorials

Designed to provide an introduction to the foundational skills necessary for machine learning

  • Learn Python (#1)

    This tutorial allows users who are completely unacquainted with programming to learn Python within a week
    Tutorial Link

  • Linear Algebra (#2)

    This tutorial introduces the necessary algebraic background for machine learning. It covers vectors, spans, vector spaces, matrices, and tensors.
    Tutorial Link

  • Calculus (#3)

    This short tutorial covers the calculus essentials for understanding machine learning. Topics include derivatives, partial derivatives, and gradients.
    Tutorial Link

  • Probability (#4)

    This tutorial covers all of the probability fundamentals which are necessary to understand probabilistic machine learning
    Tutorial Link

  • Statistics (#5)

    This tutorial introduces basic data science and querying techniques that are needed to make sense of machine learning data.
    Tutorial Link

  • Data Structures (#6)

    This tutorial covers Python in-depth and explores techniques of storing data. It also navigates the process of using a notebook
    Tutorial Link

Machine Learning Tutorials

Designed to provide an introduction to the theory behind machine learning via practical examples

  • Build a Housing Prices Predictor

    This tutorial uses Scikit-Learn and Python to predict housing prices based on pre-defined features
    Tutorial Link

  • Breast Cancer Classification

    This tutorial uses Scikit-Learn and Python to classify between benign and malignant tumors
    Tutorial Link

  • Gradient Descent Exercise

    This tutorial explains gradient descent in an iterative style while also covering the learning rate and hyperparameters
    Tutorial Link

  • Building a SVM in Python

    This tutorial explains the fundamentals of a Support Vector Machine and other kernel methods
    Tutorial Link

  • Implementing Bayesian ML

    This tutorial implements a Naive Bayes classifier and explains probability in a visual manner
    Tutorial Link

  • Constructing a K-nearest neighbors

    This tutorial uses Scikit-Learn and Python to fit a KNN classifier to a select dataset in a notebook
    Tutorial Link

Deep Learning Tutorials

Designed to provide an in-depth perspective of new developments in deep learning

  • Tensorflow Playgrounds

    This tutorial helps users to get acquainted with basic deep learning concepts and to understand the process of training and tuning a network
    Tutorial Link

  • Build a network in Keras

    This tutorial explains Keras and shows the process of designing a basic network
    Tutorial Link

  • Tensorflow I - Overview

    This tutorial explores the fundamentals of the Tensorflow library and its benefits
    Tutorial Link

  • Tensorflow II - Graphs

    This tutorial explains Tensorflow groups and automatic differentiation with tensorboard
    Tutorial Link

  • Building a GAN in PyTorch

    This tutorial explains what Generative Adversarial Networks (GANs) are and implements a simple example with the PyTorch platform
    Tutorial Link

  • Reinforcement Learning Tutorial

    This tutorial dives into the field of reinforcement learning and explores higher logic ML with the Cartpole problem. Other techniques covered include SARSA, Q-learning, and Monte Carlo Methods
    Tutorial Link

Advanced Tutorials

Designed to provide additional content to learn in the field of Artificial Intelligence

  • Complete Deep Neural Network Breakdown

    This tutorial explains perceptron, MLP, backpropagation, layers, activation functions, etc. so that you can understand how a neural network works
    Tutorial Link

  • In-Depth Convolutional Neural Networks

    This tutorial outlines the methods of convolutional neural networks. Pooling, stride, filters, convolution are all explained.
    Tutorial Link

  • Recurrent Neural Networks, LSTMs

    This tutorial explains recommenders systems with a technical focus on Recurrent networks and LSTM.
    Tutorial Link

  • GANs, Transfer and Meta Learning

    This tutorial explains how generative adversarial networks function in respect to a discriminator and generator. It also discusses transfer learning, meta-learning, and Wasserstein GANs
    Tutorial Link

  • Build a Neural Network from Scratch (Colab)

    This hands-on tutorial is designed so that the user can create a neural network from scratch. It is a way great to verify your understanding of deep learning.
    Tutorial Link

  • Breaking the Kaggle ML Titanic Code (Colab)

    This tutorial is a practical example of machine learning in action. Predict survival rate on the Titanic through simple algorithms and data preparation.
    Tutorial Link

  • Train a CNN for Image Classification (Colab)

    This tutorial outlines the methods of convolutional neural networks. Pooling, stride, filters, convolution are all explained.
    Tutorial Link

  • Learn RL Algorithms (Colab)

    This tutorial explores specific reinforcement learning algorithms like MDPs, SARSA, and implements them
    Tutorial Link

Applied AI Tutorials

  • Computer Vision #1: Introduction

    This tutorial discusses what computer vision is, its applications, and its future and challenges
    Tutorial Link

  • Computer Vision #2: Features, Pipelines, and Applications

    This tutorial explains the fundamentals of computer vision
    Tutorial Link

  • Computer Vision #3: Theory and Models

    This tutorial will dive into the theory behind the AI models used in computer vision and how they work
    Tutorial Link

  • Natural Language Processing #1: Introduction

    Coming Soon

  • Natural Language Processing #2: Features, Representations, and Models

    This tutorial explains how to represent text to AI models and covers the theory behind word embeddings such as Word2Vec
    Tutorial Link

  • Natural Language Processing #3: An Overview of State-Of-The-Art

    This tutorial is an overview of the state-of-the-art techniques that are being used in natural language processing, from the concept of attention in models to embeddings such as BERT and GPT-2
    Tutorial Link

Tutorial F.A.Q.