https://vincent0110.netlify.app/tag/deep-learning/Deep LearningWowchemy (https://wowchemy.com)en-usSun, 27 Dec 2020 00:00:00 +0000https://vincent0110.netlify.app/media/icon_hu756ae419dca872ecfcac293f58082c63_40573_512x512_fill_lanczos_center_3.pnghttps://vincent0110.netlify.app/tag/deep-learning/https://vincent0110.netlify.app/project/recipe_generator/Sun, 27 Dec 2020 00:00:00 +0000https://vincent0110.netlify.app/project/recipe_generator/<p>When we see a amazing dish from a great restaurant, we might wonder how can we make this delicacy by ourselves. With this motivation, I created a food recipe generator that takes in the photo of that specific dish and outputs the recipe to recreate that dish! However, people gets lazy sometimes. Hence, I also designed an UI to track the nearest restaurant locations that contains that dish!</p>https://vincent0110.netlify.app/project/fake_news/Tue, 25 Dec 2018 00:00:00 +0000https://vincent0110.netlify.app/project/fake_news/<p>Fake News has been more and more common throughout news media in nowadays. What can you do to discriminate true and fake news? Here, I conducted analysis between true and fake news using the Kaggle Fake News Dataset. I experimented using Latent Dirchlet Allocation(LDA) to detect news topics to see if fake news is biased towards which. However, using LDA document topic vectors did not achieve good accuracies in discriminating fake news. Deep learning methods including using pre-trained word embeddings and SOTA language models are still proven most effective!</p>