Artificial Intelligence

Spam Filter

In this post we will implement a spam filter. My motivation is dual. On one hand I am reading and experimenting with the book Natural Language Processing by Ekaterina Kockmar published by Manning. On the other hand, I am experimenting with VSCode IDE using GitHub Copilot. If interested I would suggest following the book. I purchased a copy via Amazon Prime.

I have to disclose that at this time I am a Microsoft employee and have been using Visual Studio and VSCode for many years. Continue reading “Spam Filter”

Pause Giant AI Experiments – An Open Letter

This morning I watched a 30 minute presentation titled “Why the 6-month AI Pause is a Bad Idea”. If interested watch the YouTube video to get an idea on the response by Andrew Ng and Yann LeCun. I have read a few articles on contributions from both of them to AI. As a matter of fact a few years back I took one or more courses taught by Andrew Ng.

This response is based on a request by hundreds titled: Pause Giant AI Experiments: An Open Letter. Among the petitioners you find Elon Musk, Steve Wozniak, and Yoshua Bengio, just to mention a few. As I am writing this post, the count of signatures is up to 17821 to 17931 in less than an hour. Continue reading “Pause Giant AI Experiments – An Open Letter”

First ChatGPT Post – Populate Binary Tree

Hope your weekend is going well. I will start with an unrelated event to the main subject of this post.

When I was working at my first job in Minneapolis, Minnesota the Red Cross would stop by at work for blood drives. They made it simple, so I started to give blood once a year.

Time went by and I decided to do it twice a year (one for my wife and one for me). I had my first appointment for 2023 last Friday afternoon. All went well as usual up to the point in which after the gauze was taped to my arm to protect the area from which the needle was removed. The technician offered a bandage to put pressure over the gauze to protect it for a couple hours. I have always declined and this time was no different. Continue reading “First ChatGPT Post – Populate Binary Tree”

Logistic Regression with a Neural Network mindset

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”

Neural Networks and Deep Learning Course

Towards the end of last year I started taking the Coursera course “Neural Networks and Deep Learning” taught by Andrew Ng. In a nutshell the course was great. I highly recommend it. That said; I ran into an issue with time. Allow me to explain and how I am addressing it. When done reviewing, will take the next course in the series. Continue reading “Neural Networks and Deep Learning Course”

ACM and Coursera

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”

Machine Learning – Setup

I am constantly reading and experimenting to learn things which I may apply to work projects. A few years ago I decided to spent time on and off learning machine learning (ML). With that purpose in mind, I got a number of books on different subjects (e.g., Deep Learning, Python and Statistics) which seemed to be useful to achieve my goal.

On the platform side, I started experimenting on Windows. Most things work fine but some things do not. For example, I had to wait to use Tensorflow because it ran on Linux but not on Windows. Today it seems to work on both. The same seems to hold true for Docker. Continue reading “Machine Learning – Setup”

Artificial Intelligence (AI)

I have been busy traveling and spending time with family and friends so I have not posted in a couple weeks. Sorry about that. Today is January 01, 2018, so Happy New Year. It is and for the past several days has been quite cold in this part of the country. Today we woke up to a fresh -13F. My wife and I will go to the Mall of America in an hour or so to get some steps on our Fitbits.In the past decade or so there has been a huge interest in artificial intelligence. It seems that, different aspects of AI have been creeping into applications in multiple domains (i.e., Biology, Business, Computer Science, Computer Vision, Economy, and many others). Continue reading “Artificial Intelligence (AI)”

Removing TensorFlow Warning Messages

On Revisiting TensorFlow™ I mentioned an issue with warning messages regarding SSE instructions. I understand the reason but would like to get rid of them. They clobber the output making it difficult to follow what the program is doing. Continue reading “Removing TensorFlow Warning Messages”

BotClean

I received a message from HackerRank suggesting the BotClean challenge. If interested take a look at the requirements at the following URL: https://www.hackerrank.com/challenges/botclean

I had an issue with the Output Format description. Some time ago I looked at a different challenge and my solution generated a set of steps in order to complete each task. In this case only one step may be displayed at a time. Seems that the code that invokes the method next_move() updates the coordinates and the board each time after executing a move. Continue reading “BotClean”