Welcome to my notebook! Iβm Daniel, a spanish πͺπΈ aerospace engineer living in France π«π· with a passion for learning. This blog documents my journey exploring machine learning and other topics that interest me. I believe that writing about what you learn can be not only useful for yourself but also for others following a similar path. Moreover, learning in public can spark discussions and positive exchanges.
A deep dive into the foundational paper "Long Short-Term Memory" by S. Hochreiter and J. Schmidhuber, which introduced the LSTM architecture. We'll explore the motivation behind the model, its mathematical foundations and core intuitions, as well as its properties, achievements, and relevance today.
Building upon the recently implemented and trained VggNet, we will go through and implement 'A Neural Algorithm of Artistic Style' by Gatys, Ecker and Bethge which allowed to transfer the style of one image to the content of a different one. I will dive into some of the complexities of the implementation and give some beautiful examples of the results this technique can offer.
Let's code and train VGGNet from scratch! In this post, I will explain the process of implementing this iconic CNN from designing a general architecture and using dense evaluation to optimizing training speed and actually training the network to obtain a validation top-1 and top-5 error rates of 28.33% and 9.66% respectively. I will also compare the error rates and training performance against the original paper and AlexNet.
Thank you for visiting my site! Donβt hesitate to reach out to discuss more, share your ideas or just introduce yourself. Feel free to reach me either via the contact form below or connecting with me using the links at the bottom of the page.