This morning I received a message from a discussion forum for the Graph Analytics for Big Data from the University of California San Diego by Coursera. I completed the course last year.
It is a very snowy day in the Twin Cities of Minneapolis and St. Paul. Schools are closed due to the amount of snow and low visibility. It started snowing earlier this morning and according to forecast, it should end around 09:00 PM this evening. We have already surpassed the snow amount for February according to records that go back over a century. We will be receiving more snow in the upcoming days. Will see if we set other new records.
In this post I will cover a logistic regression implementation used to determine if pictures contain a cat or not. The code is based on an edited assignment for Coursera Neural Networks and Deep Learning. Continue reading “Logistic Regression with a Neural Network mindset”
In a previous post I commented on waking up exactly at 05:00 AM. This morning I woke up around 04:10 AM. I guess there is some variation every day on how much sleep you get based on several factors (i.e., physical exhaustion, mental exhaustion, noise, temperature, food intake, among others). Continue reading “Python Basics with Numpy”
It is the last Sunday in January 2019 and is relatively cold in the Twin Cities of Minneapolis and St. Paul. The computerized mercury scale indicates -12F not taking into account wind. As usual, get up before 05:00 AM and get in my first 2 hour block of Deep Work. I am in the process of reviewing the last course I took on neural networks and deep learning. Continue reading “Numpy Vectorization – Revisited”
As you may already know, I have been taking several AI / ML related courses. I am a firm believer in always keep on learning. Some time ago I read a report about people in the USA reading books. The statistic that called my attention was: 42% of college graduates never read another book after college. That seems to me quite disturbing. Another statistic is: 57% of new books are not read to completion. To this indicates that a) readers are not committed to learning and / or books are getting worse. Continue reading “Numpy Vectorization”
It is getting late in the day for me. I am a believer in deep work so several months ago I decided to get up early morning and study for a couple hours. So far, it has worked very well for me. I have set a wakeup alarm for 05:00 AM 7-days a week. Typically I am awake between 04:30 and 05:00 so I just turn off the alarm and head down to my home office. Around 05:00 PM I feel the work day coming to an end and am ready to punt. I use EyeDefender to break every two hours. During my 5 to 10 minute breaks I walk and get some fresh water. What can I say; it works for me. On weekends I tend to just do two are three blocks. On work days I tend to do five. Continue reading “ACM and Coursera”
The workday is starting to wind down slowly. I have been doing some cosmetic changes and running tests on a medical storage server. No matter what you change you must always run tests to make sure all is well.
On my last post I covered Dijkstra’s algorithm for shortest path. Shortest path implies distance and not number of vertices traversed.
Continue reading “Neo4j and Dijkstra’s SSSP”
The motivation for this post is the Coursera class “Graph Analytics for Big Data” by the University of California San Diego I am currently taking. One of the algorithms that we briefly touched was shortest path between two nodes by Edsger Dijkstra.
The algorithm comes in different flavors. One can compute the shortest path between two nodes, the shortest paths between all nodes, among others. In this case I just went with the first approach. Continue reading “Graphs – Shortest Distance Paths”
It is Sunday morning in the Twin Cities of Minneapolis and St. Paul. Woke up around 04:30 AM and spent the next couple hours working on Machine Learning with Big Data. It is a Coursera course. Have one more week to complete this course; so far so good. After preparing and having breakfast with my best half, return to my computer. Continue reading “Transform Strings”
Have you ever wondered how computers search for text and similar images?
For example, if you use Windows, open a File Explorer window. From top to bottom the windows has the title bar, the menu bar, the tool bar. Under the toolbar there are two text fields. The one on the left displays the full path to the current folder / directory. The one on the right displays “Search <current_folder>” e.g., “Algorithms”. I have enabled in my computer “Index Properties and File Contents”. By default when you search, Windows will only search the file names and properties; not the contents of the file. Depending on your usage, you might need to index some or all the files in all folders in your computer. In my case, I perform searches in all types of documents. If you mostly use the Office Suite, you might enable search only on folders holding your *.docx files. The reason for this is that the mechanism uses additional disk and memory to operate. Continue reading “Vector Model and Similarity Search”