Machine Learning Working with Different Genetic Algorithm Representations in Python Depending on the nature of the problem being optimized, the genetic algorithm (GA) supports two different gene representations: binary, and decimal. The binary GA has only two values for its
Reinforcement Learning Play Super Mario Bros with a Double Deep Q-Network As cool as neural networks are, the first time that I felt like I was building true AI was not when working on image classification or regression problems, but when
Keras A Guide to TensorFlow Callbacks TensorFlow callbacks are an essential part of training deep learning models, providing a high degree of control over many aspects of your model training.
Keras How to Build a Variational Autoencoder in Keras This tutorial gives an introduction to the variational autoencoder (VAE) neural network, how it differs from typical autoencoders, and its benefits. We'll then build a VAE in Keras that can
NumPy Nuts and Bolts of NumPy Optimization Part 3: Understanding NumPy Internals, Strides, Reshape and Transpose We cover basic mistakes that can lead to unnecessary copying of data and memory allocation in NumPy. We further cover NumPy internals, strides, reshaping, and transpose in detail.
Neural Network Neural Architecture Search Part 4: REINFORCE Gradient and Evaluation So far we've built two major components of our neural architecture search (NAS) pipeline. In the second part of this series we created a model generator which takes encoded sequences
NLP Generating Text Summaries Using GPT-2 on PyTorch with Minimal Training In this article I will discuss an efficient abstractive text summarization approach using GPT-2 on PyTorch with the CNN/Daily Mail dataset.
NumPy Nuts and Bolts of NumPy Optimization Part 1: Understanding Vectorization and Broadcasting In Part 1 of our series on writing efficient code with NumPy we cover why loops are slow in Python, and how to replace them with vectorized code. We also dig deep into how broadcasting works, along with a few practical examples.
Machine Learning Building a Game-Playing Agent for CoinTex Using the Genetic Algorithm Games can have complex environments, where many different factors contribute to making a decision. An entire area of artificial intelligence is devoted to building game-playing agents that can make the
Python Getting Started with PyPy The Python programming language is an interface that can be implemented in many ways. Some examples include CPython which uses the C language, Jython that is implemented using Java, and
Machine Learning 5 Genetic Algorithm Applications Using PyGAD This tutorial introduces PyGAD, an open-source Python library for implementing the genetic algorithm and training machine learning algorithms. PyGAD supports 19 parameters for customizing the genetic algorithm for various applications.
Tutorial A Guide to Paperspace's Gradient Community Notebooks Gradient Community Notebooks allow users to create, run, and share Jupyter notebooks on free GPUs. In this post Gradient Community Notebooks will be introduced and the steps to get started
Neural Network Neural Architecture Search Part 3: Controllers and Accuracy Predictors In the first part of this series we saw an overview of neural architecture search, including a state of the art review of the literature. In Part 2 we then
Neural Network Neural Architecture Search Part 2: Search Space, Architecture Design and One-Shot Training In the first part of the series, we took a look at all the different angles the problem of neural architecture is being approached from. With the foundation covered, we'll
Applications Using PoseNet To Create a Snapchat-Like Eye Filter for Android PoseNet is a computer vision deep learning model used for estimating a person's physical position. Based on MobileNet, it can be deployed to mobile devices and takes even less time
Data Science Implementing The Levenshtein Distance for Word Autocompletion and Autocorrection The Levenshtein distance is a text similarity measure that compares two words and returns a numeric value representing the distance between them. The distance reflects the total number of single-character
Series: GauGAN Understanding GauGAN Part 4: Debugging Training & Deciding If GauGAN Is Right For You In this post we cover how to tackle common training issues that may arise with GauGAN. We conclude with advice on whether GauGAN will fit your business needs or not.
Series: GauGAN Understanding GauGAN Part 3: Model Evaluation Techniques Hi folks, welcome to the third part of the GauGAN series. In the last two parts we've covered the components and losses of GauGAN, and how to set up custom
Series: GauGAN Understanding GauGAN Part 2: Training on Custom Datasets In Part One, we covered the basic components of GauGAN as well as the loss functions it makes use of. In this part, we'll cover the training details and see
Deep Learning Deploying Deep Learning Models Part 2: Hosting on Paperspace Gradient is a Paperspace product that simplifies developing, training, and deploying deep learning models. The platform provides infrastructure automation and a software development kit for machine learning developers. For creating
Generative Models Implementing CycleGAN for Age Conversion If you've been on any sort of social media this year, you've probably seen people uploading a recent picture of themselves right next to another picture of what they'll look
Series: Gradient Descent with Python Implementing Gradient Descent in Python, Part 4: Applying to Any Number of Neurons In this tutorial we extend our implementation of gradient descent to work with a single hidden layer with any number of neurons. Part 4 is divided into two sections. In
Tutorial Neural Machine Translation with TensorFlow If  you are a fan of Google translate or some other translation service, do  you ever wonder how these programs are able to make spot-on translations from one language to
Series: Gradient Descent with Python Implementing Gradient Descent in Python, Part 3: Adding a Hidden Layer Hello again in the series of tutorials for implementing a generic gradient descent (GD) algorithm in Python for optimizing parameters of artificial neural network (ANN) in the backpropagation phase. The
Tutorial Unpaired Image to Image Translation with CycleGAN Yann LeCun, director of AI research at Facebook and Professor at NYU described Generative Adversarial Networks, GANs as the most interesting idea in Machine Learning in the last 10 years.
