Blog Posts - machine-learning

Liam
Apr 23, 2016
Blogpost Cover

TensorFlow Udacity 1_notmnist - Part 6

Basically 1_notmnist is to learn how to display data in Jupyter Notebook. Besides, it also let us know on sklearn - a python machine library - so that we can then compare with TensorFlow. This is the exact ipynb file at Tensorflow Github Repo.

View
Liam
Apr 16, 2016
Blogpost Cover

TensorFlow Udacity 1_notmnist - Part 5

Basically 1_notmnist is to learn how to display data in Jupyter Notebook. Besides, it also let us know on sklearn - a python machine library - so that we can then compare with TensorFlow. This is the exact ipynb file at Tensorflow Github Repo.

View
Liam
Apr 09, 2016
Blogpost Cover

TensorFlow Udacity 1_notmnist - Part 4

Basically 1_notmnist is to learn how to display data in Jupyter Notebook. Besides, it also let us know on sklearn - a python machine library - so that we can then compare with TensorFlow. This is the exact ipynb file at Tensorflow Github Repo.

View
Liam
Apr 02, 2016
Blogpost Cover

TensorFlow Udacity 1_notmnist - Part 3

Basically 1_notmnist is to learn how to display data in Jupyter Notebook. Besides, it also let us know on sklearn - a python machine library - so that we can then compare with TensorFlow. This is the exact ipynb file at Tensorflow Github Repo.

View
Liam
Mar 26, 2016
Blogpost Cover

TensorFlow Udacity 1_notmnist - Part 2

Basically 1_notmnist is to learn how to display data in Jupyter Notebook. Besides, it also let us know on sklearn - a python machine library - so that we can then compare with TensorFlow. This is the exact ipynb file at Tensorflow Github Repo.

View
Liam
Mar 19, 2016
Blogpost Cover

TensorFlow Udacity 1_notmnist - Part 1

Basically 1_notmnist is to learn how to display data in Jupyter Notebook. Besides, it also let us know on sklearn - a python machine library - so that we can then compare with TensorFlow. This is the exact ipynb file at Tensorflow Github Repo.

View
Liam
Feb 07, 2016
Blogpost Cover

Udacity Deep Learning Course By Google

FYI, the course link is https://www.udacity.com/course/deep-learning--ud730. This course takes approximately 3 months with assumption 6hrs/wk (work at your own pace).

View
Liam
Nov 14, 2015
Blogpost Cover

Tensorflow (Machine learning toolset Open Source by Google)

On 10th November, I saw the news that Google open sourced Tensorflow. As a programmer that is passionate towards AI, this is a thing that I must try out.

View
Liam
Oct 31, 2015
Blogpost Cover

Kaggle titanic challenge with Julia commentary

Recently Julia is on the trend, due to its purpose of becoming an easy-to-use scripting language, while giving near to C performance speed. I always see it as combination of Python + R + C, while some might think it as Python + Matlab + C

View
Liam
Jul 11, 2015
Blogpost Cover

Trying to use Torch7 CUDA

CUDA® is a parallel computing platform and programming model invented by NVIDIA. It enables dramatic increases in computing performance by harnessing the power of the graphics processing unit.

View
Liam
Jul 04, 2015
Blogpost Cover

Coursera course review - Machine Learning by Andrew Ng

This course provides a broad introduction to machine learning, datamining, and statistical pattern recognition. Topics include:

  • Supervised learning (parametric/non-parametric algorithms, support vector machines, kernels, neural networks).
  • Unsupervised learning (clustering, dimensionality reduction, recommender systems, deep learning).
  • Best practices in machine learning (bias/variance theory; innovation process in machine learning and AI).
View
Liam
Jun 20, 2015
Blogpost Cover

Kaggle titanic challenge with torch7

Kaggle titanic challenge is a famous knowledge competition which many new Kaggler will try their first Kaggle competition. Since there are currently no tutorial to solve this challenge with artificial neural network, I decided to use torch7 to compete in this competition. FYI, click here to get the data.

View
Liam
Jun 05, 2015
Blogpost Cover

Kaggle contest review - Bike Sharing Demand

Bike sharing systems are a means of renting bicycles where the process of obtaining membership, rental, and bike return is automated via a network of kiosk locations throughout a city. Using these systems, people are able rent a bike from a one location and return it to a different place on an as-needed basis. Currently, there are over 500 bike-sharing programs around the world.

View
Liam
May 24, 2015
Blogpost Cover

Paper reading - Weight Uncertainty in Neural Networks

Backpropagation, is a well known learning algorithm in neural network. In the algorithm, the weight calculated is based on the out put of the result. To prevent overfitting and introduce more uncertainty, its often comes with L1 and L2 regularization.

Weights with greater uncertainty introduce more variability into the decisions made by the network, leading naturally to exploration

View