A Deep Learning project focused on Convolutional Neural Networks (CNN) and their applications in AI.
This project delves into the world of Artificial Neural Networks and explores their wide-ranging applications in the field of artificial intelligence. Convolutional Neural Networks (CNN) are a type of neural network that have been widely used in image and video recognition. CNNs are inspired by the structure of the animal visual cortex and can automatically learn to recognize visual patterns such as edges and shapes. The maximum accuracy reached was 99.25% in 58 epochs.
In this project, a CNN is implemented from scratch using Java without any machine learning related library, and trained the model on a mnist dataset, which consists of 5,620 8x8 gray-scale images in 10 classes. Google Colab played a pivotal role in this project as it served as a valuable resource - a free cloud-based Jupyter notebook environment that granted access to essential testing environments.
You can try out this implementation of CNN on Google Colab by clicking on this link:
https://colab.research.google.com/drive/1UjcC4Cm2_UlceRvDiEEb3FQzJLsSwNjr?usp=sharing
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent