![](https://cdn.myportfolio.com/7663c5f5-2ffa-4a2c-9035-864fe5ea1522/9b594868-929a-4689-a3eb-5172c0685f1b_rw_1920.jpg?h=e2f6f5d71120b4454deac009444249bd)
![](https://cdn.myportfolio.com/7663c5f5-2ffa-4a2c-9035-864fe5ea1522/e0953a4e-a129-446b-ad7e-b487206091ba_rw_1920.jpg?h=a949c0291911526beb02a73205f91036)
![](https://cdn.myportfolio.com/7663c5f5-2ffa-4a2c-9035-864fe5ea1522/3ae8727b-81a2-43a1-a07d-deb17fe5be72_rw_1920.gif?h=bb12f788382577595f56c3f87dc4b462)
![](https://cdn.myportfolio.com/7663c5f5-2ffa-4a2c-9035-864fe5ea1522/7357090f-f124-4ef0-ae36-30ebe150562e_rw_1920.jpg?h=527315caf63f289e9081422670c77135)
![](https://cdn.myportfolio.com/7663c5f5-2ffa-4a2c-9035-864fe5ea1522/a7a3838f-3fe5-4edc-bc98-23074ba89df9_rw_1920.jpg?h=f221ca20ef317203abe2296dbf64ce1e)
![](https://cdn.myportfolio.com/7663c5f5-2ffa-4a2c-9035-864fe5ea1522/8905ab94-a4da-4ef3-9114-4e60ab713a3b_rw_1920.gif?h=46f5255c27d9aca06bcacdabb6823524)
![](https://cdn.myportfolio.com/7663c5f5-2ffa-4a2c-9035-864fe5ea1522/7636dd2b-183c-4877-8c61-4b9de1b0c4db_rw_1920.gif?h=c328c90d4ad373440fd267e003285943)
![](https://cdn.myportfolio.com/7663c5f5-2ffa-4a2c-9035-864fe5ea1522/db906de2-d224-476c-a352-917fffc65929_rw_1920.gif?h=3d5f69aa5250b0012f75327b226c0fce)
![](https://cdn.myportfolio.com/7663c5f5-2ffa-4a2c-9035-864fe5ea1522/53efd4e2-29f0-4130-8866-724bd6f862df_rw_1920.gif?h=371c864bf3bfedb47be2c667c1accd33)
This research investigates the potential of learning-based models, particularly Autoencoder (AE) networks, in enhancing creative inquiries within computer-aided design (CAD) systems. It challenges the conventional role of CAD as mere task executors, aiming to develop a system that offers reciprocal interaction and design suggestion generation. The study explores their capability to represent and learn various design approaches and intentions in a lower-dimensional latent space by training AE networks on problem-specific datasets. This work represents the first stage in understanding the reconstruction capabilities of AE networks through synthetic datasets tailored to specific design problems. Collaborators: Shakthi Suresh, Chris McComb