A dumb A.I.
Today, my day did not start at 5:30 am. It started at 2:30 am when a funny smell polluted our room. We woke up from the smell as it smelt like burnt plastic. We were not sure if it was caused by something in-house or it was coming from outside. We went out to check and the smell was stronger outside. There was nothing we could do, so we closed all the windows and went back to sleep.
Sleep interruption is no ideal for me. At 5:00 am when my alarm rang, I did not get up. I knew if I did, my day would be a disaster. I would have gotten a headache, would have felt drowsy and just not optimum. I got up at 7:00 am. Which again is not too bad. Considering I had an interrupted sleep pattern.
I woke up, and this time I 1st did my work out. After which I had a shower, and ran to the chiropractor. I had an appointment at 9:30 am. I have a lot of misalignment in my spine. She started to fix them and told me to come to visit her 2 times a week for a minimum of 4-6 weeks. I said I will see based on my budget.
I came home to train my N.N. What I trained was very dumb. But it has got to do with me not having enough samples. For an N.N (Neural Network) to be effective, it needs to be trained on a large number of datasets. I only had a handful. This is for the N.N to classify the website's section and the column count. If I show it an image, it should tell me how many columns are present. A simple A. I will be effective in automating website building.
Later in the day, I did not do much. I have been slacking quite a bit. I did however learn of a few new courses that can help me with ANTSHIV Robotics. MAking autonomous drones requires expertise in a lot of areas. A.I., machine dynamics, aerodynamics, flight dynamics, 3d modeling and rendering, industrial design, camera and imaging, embedded systems, electronics, electrical drives and motors, radio, software skill, control systems imaging, and 3d geometry, etc. That is a lot of disciplines.
My job is to master as much as I can to make a simple autonomous drone fly. Nothing is simple in this project. But the more I strengthen my tree of knowledge, the faster I can progress. I was looking for learning material on 3d geometry (Spatial Computational Thinking) and dynamics. That is what I spent the evening doing. In the afternoon, I was browsing what batteries I would need, what components I would need to fabricate the onboard computer on the quadcopter.
I must now spend less time browsing and more time on learning and executing. Which is to say, I want to get the Machine learning course completed quickly, an introduction to Aeronautical Engineering done, and then study more on aerodynamics and rigid body dynamics. A lot of learning, a lot to execute. Time prioritization is critical. Tomorrow morning I will focus the 1st 1 hour or so on aerodynamics and the next one hour on machine learning. I will also collect more images to train the N.N for website classification.
Later in the afternoon, I will work on the radio module.
Sleep interruption is no ideal for me. At 5:00 am when my alarm rang, I did not get up. I knew if I did, my day would be a disaster. I would have gotten a headache, would have felt drowsy and just not optimum. I got up at 7:00 am. Which again is not too bad. Considering I had an interrupted sleep pattern.
I woke up, and this time I 1st did my work out. After which I had a shower, and ran to the chiropractor. I had an appointment at 9:30 am. I have a lot of misalignment in my spine. She started to fix them and told me to come to visit her 2 times a week for a minimum of 4-6 weeks. I said I will see based on my budget.
I came home to train my N.N. What I trained was very dumb. But it has got to do with me not having enough samples. For an N.N (Neural Network) to be effective, it needs to be trained on a large number of datasets. I only had a handful. This is for the N.N to classify the website's section and the column count. If I show it an image, it should tell me how many columns are present. A simple A. I will be effective in automating website building.
Later in the day, I did not do much. I have been slacking quite a bit. I did however learn of a few new courses that can help me with ANTSHIV Robotics. MAking autonomous drones requires expertise in a lot of areas. A.I., machine dynamics, aerodynamics, flight dynamics, 3d modeling and rendering, industrial design, camera and imaging, embedded systems, electronics, electrical drives and motors, radio, software skill, control systems imaging, and 3d geometry, etc. That is a lot of disciplines.
My job is to master as much as I can to make a simple autonomous drone fly. Nothing is simple in this project. But the more I strengthen my tree of knowledge, the faster I can progress. I was looking for learning material on 3d geometry (Spatial Computational Thinking) and dynamics. That is what I spent the evening doing. In the afternoon, I was browsing what batteries I would need, what components I would need to fabricate the onboard computer on the quadcopter.
I must now spend less time browsing and more time on learning and executing. Which is to say, I want to get the Machine learning course completed quickly, an introduction to Aeronautical Engineering done, and then study more on aerodynamics and rigid body dynamics. A lot of learning, a lot to execute. Time prioritization is critical. Tomorrow morning I will focus the 1st 1 hour or so on aerodynamics and the next one hour on machine learning. I will also collect more images to train the N.N for website classification.
Later in the afternoon, I will work on the radio module.
The Blog of Anthony Shivakumar
Subscribe to emails from Anthony
First Name
Last Name
Email