Introduction

General Adversarial Networks are able to create incredible projects and ideas, like creating synthetic faces from scratch (see the previous blog for more on that). In order to work, they use something called a latent space, a gaussian distribution of random numbers in a given dimension. This latent space is independent of the creator, there is no way to adjust its values in order to create only a specific type of data. This creates a limitation in the use of regular GANs. If we had a dataset of fashion items and we wanted to use it to create new fashion…


Generative Adversarial Networks are known to require good hardware and time to train. Because of this, certain optimizations and standards have come to be so as to reduce the time for training in GANs. In this blog I will list a few of these tips that help create better GANs faster. Most of these come from books and videos such as Jason Brownlee’s General Adversarial Networks with Python.

The first tip starts with the latent space. The latent space is what defines the input dimensions for the generator part of the GAN model. This is typically created by a simple…


As with the last blog, here is the link to the GitHub repository to see the code in action. When the notebook is clicked on, it will automatically show results, but it is also easy to run yourself.

General Adversarial Networks, aka GANs, are a useful architecture for generating images from scratch. Examples of uses of GANs include Nvidia’s playground website: https://www.nvidia.com/en-us/research/ai-playground/. Here they provide examples of using GANs, ranging from aging your pet to creating detailed works of art from simple illustrations. In this project, I used GANs to synthetically create human faces. As with the last blog, this…


To view the code that I wrote for this project, view and open the following github link: https://github.com/arnavkartikeya/EmotionDetection

Facial emotion detection is a common issue focused on in the field of cognitive science. An attempt to understand what exactly we as humans see in each other that gives us insight into other emotions is a challenge we can approach from an artificial intelligence side. While I don’t have enough experience in psychology or even artificial intelligence to determine these factors, we can always start off by building a model to determine at least the start of this question.

Establishing the baseline

Fer2013 is…


Tell us a little bit about yourself! What are your hobbies? Why are you studying artificial intelligence? Anything else we should know?

Hi I am Arnav Kartikeya, a junior at Cupertino High School. I am mostly interested in cognitive and computer science, which is why I have chosen to learn more about the field of artificial intelligence. My main reason is to try and understand how us as humans learn and understand the world around us, and this can be done by creating models to see how an AI would learn. …


Neural networks are a fascinating field of computer science that attempts to model the brain in a mathematical sense. Unfortunately, they are nowhere near the level of complexity as the human brain, and will most likely not be in the near future. However, while there is no single network that can match the brain in its complexity and accuracy, there are specific networks that can rival the accuracy and speed of the human mind, though they often lag in the accuracy department.

One such example of this is the recurrent neural network, typically shortened to RNN. The RNN is significantly…


Artificial Intelligence is a term that is thrown around a lot when it comes to new and revolutionary technologies. But what exactly does Intelligence mean? Can I say I created something intelligent if it can answer a series of pre-written questions?

Understanding what Intelligence is may not seem necessary, but it was vital in the creation of cognitive science and AI. The original plane design was meant to mimic a bird. If mother nature built it, isn’t it safe to assume that it would be best to just copy from it? Of course, this turned out not to be the…


Recently before school began, I attended a short program held by the Ohio State University about cognitive science and humanities, hosted and created by professors Fredrick Luis Aldama and Andrew Leber. The program was insightful in many ways, because I learned about many different fields, ranging from gender studies to storytelling, and how they all relate to cognitive science.

The biggest revelation I had during this program was how narrow-minded my approach was too artificial intelligence. I always just associated it with computer science and mathematics and judged it as a subject or field of study. While these are not…


Neural networks are a fascinating field of computer science that attempts to model the brain in a mathematical sense. Unfortunately, they are nowhere near the level of complexity as the human brain, and will most likely not be in the near future. However, while there is no single network that can match the brain in its complexity and accuracy, there are specific networks that can rival the accuracy and speed of the human mind, though they often lag in the accuracy department.

One such example of this is the recurrent neural network, typically shortened to RNN. The RNN is significantly…


Part of the reason I enjoyed computer science so much was the challenge of taking human logic and translating that to computer logic. As a human, we can look at a list of integers and holistically find a number in the list, that is, we can see most of the list at once. For a computer, this is not possible, and so we need to find a new way for the computer to accomplish this task. Typically, when I find myself completing classic computer science problems, I often learn more about the brain and how we think through these problems…

Arnav Kartikeya

A high school student interested in cognitive science and programming

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store