Building AlexNet with TensorFlow and Running it with AWS SageMaker
In the last post, we built AlexNet with Keras. This is the second part of AlexNet building. Let’s rewrite the Keras code from the previous post (see Building AlexNet with Keras) with TensorFlow and run it in AWS SageMaker instead of the local machine. AlexNet is in fact too heavy …
Building AlexNet with Keras
As the legend goes, the deep learning networks created by Alex Krizhevsky, Geoffrey Hinton and Ilya Sutskever (now largely know as AlexNet) blew everyone out of the water and won Image Classification Challenge (ILSVRC) in 2012. This heralded the new era of deep learning. AlexNet is the most influential modern …
Introduction to Dense Layers for Deep Learning with TensorFlow
TensorFlow offers both high- and low-level APIs for Deep Learning. Coding in TensorFlow is slightly different from other machine learning frameworks. You first need to define the variables and architectures. This is because the entire code is executed outside of Python with C++ and the python code itself is just …
Introduction to Dense Layers for Deep Learning with Keras
The most basic neural network architecture in deep learning is the dense neural networks consisting of dense layers (a.k.a. fully-connected layers). In this layer, all the inputs and outputs are connected to all the neurons in each layer. Keras is the high-level APIs that runs on TensorFlow (and CNTK or …
How To Create Your Own Personal Data Science Computing Environment In AWS
Running a training algorithm is such a time-consuming task when you are building a machine learning application. If you are developing it with your computer, you cannot do anything else for a long period of time (hours and maybe days) on that machine. Especially when we do parallel processing using …
Predict Internet Popularity By Optimising Neural Networks With Python
In the previous post, we used grid search to find the best hyper parameter for the neural network model with R’s caret package. Here, let’s use Python and scikit-learn package to optimise a neural network model. Just like the caret package, scikit-learn has a pre-built function for hyper parameter search. …
How To Save Machine Learning Models In R
Once you finish training the model and are happy with it, you may need to consider saving the model. Otherwise, you will loose the model once you close the session. The model you create in R session is not persistent, only existing in the memory temporarily. Most of the time, …
Predict Internet Popularity By Optimising Neural Networks With R
Writing code to do machine learning is easy. What makes it difficult is the optimisation. By large, there are two ways to optimise your model. Feature selection & transformation Model parameter optimisation Both are hard-core topics and neither can be covered in this post. Feature selection and transformation often require …
How To Deploy Spark Applications In AWS With EMR and Data Pipeline
Once you create an awesome data science application, it is time for you to deploy it. There are many ways to productionise them. The focus here is deploying Spark applications by using the AWS big data infrastructure. From my experience with the AWS stack and Spark development, I will discuss …
How To Do Sentiment Analysis On Your Favourite Book With R
I love dissecting and analysing my favourite books by reading them again and again, discussing them with my like-minded friends, getting to know the authors and reading other people’s writings about them. My obsession with books lead me to thinking, how can I visualise them in interesting ways? Making Word …