44. The Four Waves of AI
THE FOUR WAVESI’m currently reading a book called AI SUPER-POWERS by Dr. Kai-Fu Lee, and the concept of the 4 waves of AI was very interesting, so I want to share what I’ve learned here. In the book, he explains…
THE FOUR WAVESI’m currently reading a book called AI SUPER-POWERS by Dr. Kai-Fu Lee, and the concept of the 4 waves of AI was very interesting, so I want to share what I’ve learned here. In the book, he explains…
PART 2I’ve tried generating faces to see how many images and epochs you need to get something recognizable. For part 1, I’ve done 23 epochs with about 20,000 images, and found that the machine was able to create something recognizable…
DMPDuring a DMP app development, I bump into many performance issues since I want to… A) Display chosen dataB) Apply desired data-preprocessing methods with an ENORMOUS amount of data as soon as possible.It’s been about 4 months since I’ve joined…
How Much Is Enough? The last time I used gan(Generating cityscapes), the output was not recognizable due to a lack of data. So, as for my next step I wanted to find out how much data and epochs you need…
WEB-DEVOne of the options for delivering an AI application is creating a USER INTERFACE so that the clients can use the AI app even without any knowledge of programming. For this time, I’ve decided to try it out on AWS.…
DOCKERI’m currently working on a service using Docker, and recently I’ve found something that might be very useful called MULTI-STAGE BUILD so I’d like to share it here. CONCEPTFor all of my previous works, I’ve been using OPTION 1 from…
PREPARING DATAWhen starting an AI project, 80% of the work is on cleaning data for the model. In most cases, the data are not clean and the data source is not centrally managed. That’s when a data management platform comes…
TUNINGI’ve learned that the predictions machine-learning models make, vary widely depending on the hyperparameters. However, manually testing these hyperparameters can be quite inefficient. In order to resolve that, I found a software framework to automate this process called Optuna, so…
GENERATIVE ADVERSARIAL NETWORKThere is a class of machine learning framework called GAN which generates new data from data. One of the most popular use cases for GAN is generating people’s faces who don’t exist. As I was learning more about…
THE GAPI was listening to a podcast called “AI TODAY” by Cognilytica the other day and their topic about this blog’s title was quite intriguing, so I want to share it here. According to TechRepublic, 85% of AI projects eventually…