What's next after Deep Learning courses?


Well...for the past weeks, we have been rushing to complete the Andrew Ng's Deep Learning module so that we can complete it in a month. 

About Andrew's Ng Deep Learning @ Coursera:

For those who do not know, there are 5 courses for this Deep Learning module and each course will take about a few weeks to complete. You will have to input your credit card details before you can access the 7-days free trial for this module. Pretty smart way to lock in customers uhhh...Anyway, after the free trial period, if you wish to continue, you have to pay USD 49 per month. Otherwise, REMEMBER to 'un-enroll' the course.  

 https://www.coursera.org/specializations/deep-learning

Confessions

To be honest, we have only completed 99% of the module as we didn't do the last programming assignment ðŸ˜³.


Why didn't we continue?

Initially, we were very motivated to finish the whole module since we have already prepaid for the first month and we wanted to setup our AI business asap. Every day, we would go out to coffee shops to attend the online courses. For the first 4 courses, we didn't have much difficulties in the assignments as we were able to google the issues or get clues from the Coursera forums.

When it comes to the 5th course, we became impatient and restless. We started to lose focus and didn't pay close attention to the lectures. For the last few programming assignments, we had to implement in Keras and we didn't have any prior knowledge about it. Yet, we didn't even bother to research and also we were reluctant to re-watch the whole lectures again. We just smoked our way through by hitting the CTRL + C and CTRL + V buttons in Google and forums. However, our luck didn't last till the end. We were stuck at the final assignment for a few days and we felt so lost and frustrated. We thought of just stopping where we were and forget about the last assignment since we are not intending to get the digital certificate anyway.

We took a few days off...and eventually moved on as we thought why not try out some simple projects first?!?

"The best way of learning about anything is by doing"

by Richard Branson


By applying what we have learnt, we would then realize what we know and don't know. From there, we are then able to carry out more appropriate steps towards our goals.  

So, what's our next move? 

Right now, we want to build a model to predict the English Premier League (EPL) results. We are in the midst of organizing the raw data and extracting the relevant features. Stay tune for our updates!


Thanks for taking time to read this boring post. In the future. we will be documenting our AI learning journey in this blog to share our experience and thoughts..

Leave us a comment if you have any thoughts!



Comments

Post a Comment

Popular posts from this blog

How to connect Python to MySQL Workbench

Image
Step-by-Step Guide 1) Download MySQL: For Windows user , you can download  MySQL Installer that allows you to install all the products in one package. Link as follows https://dev.mysql.com/downloads/windows/installer/8.0.html Download MySQL Installer (For Windows only!) Begin download Otherwise, you can download the product 1 by 1  (Remember to select your Operating System for all!) MySQL Workbench  MySQL Connector / Python   (Note: You have to download Python first. And remember to select the OS and Python version!) MySQL Community Server For Windows users... 2) How to setup MySQL Installer We are going to show how to download and install MySQL Community Server only... Double click the file and install it Once it has finished installing, you will see this window below and click on the 'Add' option Click 'Add' option Agree on their License terms and click 'next' Agree on License Terms Selec...
Read more

Predict EPL results (Part 2: Neural Network example)

Image
Neural Network explained Artificial Neural Network is a model that receives input in vector/matrix form and uses them to compute the output  It is made up of 3 different layers namely input layer, hidden layer and output layer.  Each layer is made up of 1 or more artificial neurons (aka nodes)  The nodes are interconnected with one another Each node is assigned to a weight value denoted by  w  that determines how much emphasis is given to the learned information extracted from the raw training data  Note: A   Neural Network with 1 hidden layer is known as  Shallow Neural Network Types of Neural Networks Feedforward Neural Network Convolutional Neural Network (CNN) Recurrent Neural Network - Long Short Term Memory (LSTM) Networks Recursive Neural Network Neural Network Architecture The figure below shows a  Neural Network Architecture  that is made up of n  features,  h  hidden layers and ...
Read more

Bias and Variance in Machine Learning

Sorry for the lack of updates...Have been rushing to complete the Machine Learning course as fast as possible... Good news!!! We managed to survive through the whole course!!!! Hahaha Summary of Week 6 lesson: Some definitions first before delving into the details... Bias:  The hypothesis is known to be biased if it tends to overestimate or underestimate a parameter Variance:  The hypothesis is known to have high variance if the data are far away from its average value Given the complexity of some data, a linear regression may not be able to formulate an accurate prediction. As the linear regression only factors in 1 specific feature of the data, the 'best-fit' line does not fit the data well enough. Such under-fitting problem leads to high training costs and also causes the hypothesis to be biased. Ways to reduce the bias: Add more features / Increase the degree of the polynomial Decrease λ  Use larger neural network As mentioned a...
Read more