My expertise lies at the intersection of academic theory and real-world implementation. I thrive on turning state-of-the-art models into robust solutions that excel in the dynamic landscape of data projects. With an extensive background in both the theoretical foundations and hands-on application of Machine Learning and Deep Learning techniques, I bring a unique blend of knowledge and experience to the table.
Over the course of my career, which spans five years, I have successfully deployed ML/DL solutions across a wide array of domains. Whether it's computer vision, natural language processing, recommendation systems, or any other area, I have consistently delivered results that meet the demands of modern data-driven industries.
My mission is to make the complex world of Machine Learning and Deep Learning accessible and practical for businesses and projects of all sizes. I believe that the power of data should be harnessed to its fullest potential, and I am here to help you navigate the journey from theory to scalable, reliable solutions.
Explore my GitHub repositories and discover how I can assist you in transforming your data challenges into opportunities for success. Together, we can bridge the gap between cutting-edge research and the practical implementation that drives innovation in today's data-driven world.
-
🔭 Paper that I have implemented from scratch ...
- Yolo V3, Show, Attend and Tell: Neural Image Caption Generation with Visual Attention, Convolutional Sequence to Sequence Learning, Sequence to Sequence Learning with Neural Networks, Attention Is All You Need, Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation, Neural Machine Translation by Jointly Learning to Align and Translate, U-Net: Convolutional Networks for Biomedical Image Segmentation, A Neural Algorithm of Artistic Style, Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks(DCGAN),
- Improved Training of Wasserstein GANs (WGANGP), Wasserstein GAN (WGAN), Conditional Generative Adversarial Nets (cGAN), Image-to-Image Translation with Conditional Adversarial Networks (PIX2PIX), Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks (CycleGAN), Progressive Growing of GANs for Improved Quality, Stability, and Variation (ProGAN), Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network (SRGAN).
-
🌱 I’m currently learning ...
- Generative AI
- Audio Signal Processing
-
📫 How to reach me: ...
-
😄 Pronouns: ...
- He/Him/His
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent