I don’t quite understand what is meant by the first sentence. Should it be deep learning in general, previous literature, or deep learning courses that are tied up in implementation details? Of course, you need to consider the implementation details when writing a deep learning application?
“For the deep learning framework, we will use…”
“Jax is easy to learn because it’s essentially numpy with automatic differentiation and GPU/TPU-acceleration”. I would try to avoid sounding like things are easy or obvious. We have all experienced frustration with textbooks that present things as trivial or easy, while we struggle to understand. Some students may not know what numpy, automatic differentiation or GPU/TPU-acceleration is?
“In this book, I use…” -> “In this book, we will use...”.
The description of the different frameworks could be clearer and more concise. There are many misplaced side notes, like “This is just my reasoning for the choice of framework.”
“Of course, you can use Jax for complete models and show new implementations in Keras.” I don’t understand this, and would avoid “of course”. What is the difference between complete models and new implementations?
Long and unclear sentence: “Ultimately, this book presents the equations and implementation details so that you should learn concepts that are independent of the framework and you should be able to quickly pick up PyTorch or develop more competence in Keras quickly.” Again, I would avoid writing that students “should be able to do things quickly”. Some students may struggle with the material and feel discouraged if they read they “should learn quickly”.
“One of the most common mistakes I see of students...” -> “One of the most common mistakes I see from students...”?
whitead
commented
3 years ago
I don’t quite understand what is meant by the first sentence. Should it be deep learning in general, previous literature, or deep learning courses that are tied up in implementation details? Of course, you need to consider the implementation details when writing a deep learning application?
“For the deep learning framework, we will use…”
“Jax is easy to learn because it’s essentially numpy with automatic differentiation and GPU/TPU-acceleration”. I would try to avoid sounding like things are easy or obvious. We have all experienced frustration with textbooks that present things as trivial or easy, while we struggle to understand. Some students may not know what numpy, automatic differentiation or GPU/TPU-acceleration is?
“In this book, I use…” -> “In this book, we will use...”.
The description of the different frameworks could be clearer and more concise. There are many misplaced side notes, like “This is just my reasoning for the choice of framework.”
“Of course, you can use Jax for complete models and show new implementations in Keras.” I don’t understand this, and would avoid “of course”. What is the difference between complete models and new implementations?
Long and unclear sentence: “Ultimately, this book presents the equations and implementation details so that you should learn concepts that are independent of the framework and you should be able to quickly pick up PyTorch or develop more competence in Keras quickly.” Again, I would avoid writing that students “should be able to do things quickly”. Some students may struggle with the material and feel discouraged if they read they “should learn quickly”.
“One of the most common mistakes I see of students...” -> “One of the most common mistakes I see from students...”?