Deep Learning with Python

It's been years since I read a software book cover to cover, methodically. This one is well worth a second or third read if you are interested in Tensorflow and Keras or neural networks in general. His crumpled paper analogy early on alerted me to the intuitive depth of this book. You do need just enough understand of linear algebra to appreciate what a vector space is to fully appreciate this analogy (this is not as hard as it sounds either, I promise. If you can do the first few videos on Khan Academy for linear algebra or half hour with a good tutorial, you'll be more than fine). He avoids too much reliance on equations as the means of explanation, which for me, with barley enough linear algebra to tell a dot from a cross product, is great. To be clear, it is best (in this whole field actually) if you understand differential calculus sufficient to appreciate the result of the power rule is a function not a number, and the afore mentioned linear algebra. If you spend an hour assuring yourself you can at least vaguely grasp this, then the more involved explanations will be very straightforwards. I emphasise this aspect because it's my own weakness - I have to work to focus on simple equations. To make simple to intermediate models, following this book you still won't need much, if any depth of the maths skill, so don't let my mention of it out you off. It's a great solidly practical and wide ranging exploration of doing many tasks with deeplearning. I recommend it with the Coursera developer certificate from DeepAi to any total beginner in neural networks. Python knowledge needed? I've coded with Python for approximately ten hours of actual experience but I am a software developer. So either good experience in other languages or the ability to work with simple python constructs and classes. A beginners course will help suffice it if you really don't have either. The second book pictured is also excellent, worth taking in when you've gotten halfway through this one. The author recommends it and he's absolutely right.

To me, this book is great—it clarifies the concepts very well. However, it would be much better if it used PyTorch instead of Keras.

Deep learning tutorial, excellently balanced between hands-on examples and deeper concepts explained in an intuitive, non-mathematical way. Very well structured chapters explain step by step the workflow for framing, developing and deploying a real world model. Easy to follow, uses informal language, but with great depth. Highly recommended.

Well-structured

Delivered wrapped with vynil cover and good vivid colours in content

Whilst a little tough to follow for a beginner (which I am), I have found this a useful entry point to understanding neural networks.

I'm on page 299 as I write this and and I'm a software engineer with a physics PhD who wanted a refresher on neural networks and to try some deep learning methods using tensorflow 2.0 on a side project I'm working on. The book starts with a surface level overview of deep learning and avoided specific computer setup information (which is fine, to some extent) but it continuined in a similar manner throughout the rest of the book. He specifically says he won't include any mathematical expressions but he also doesn't give any explanation on how it works, just surface level descriptions. I'd have expected some theory (and high quality diagrams and labelling in lieu of explaination - incl axes labels in places) but it's really just an informally written walkthrough and feels like something is missing. You end up relying on a lot of background knowledge and doing a lot of leaping yourself. Perhaps a good primer for the unitiated who don't want the detail and want something working faster than I do but was disappointed with every page turn. There's probably a good book out there that does example code with underlying theory/explaination that leaves you coming away with a better understanding (rather than just knowledge/awareness) but this isn't it. Reminds me of a bad lecture/tutorial where the guy is just trying to get through his material in too short a time period and get the mixed ability class to try the tasks and come back to him with problems. Otherwise print is of good quality, some diagrams rushed but come out well, code formatting is reasonable. Requires basic python knowledge and familiarity with numpy. For its faults, this book does give you an overview of tensorflow by exploring some methods - no prior experience needed.

This is a great and informative book and it really just gets to the point on how to start learning NN and deep learning, But the actual book itself is so cheap, they clearly have cut corners on the paper for the coloured ink, you can can see straight through to the other paper to the point you can read the next page without turning over, also the actual overall package is very flimsy and I think after a few more uses this book will just disintegrate. I wouldnt recommend buying this book if you are just going to read electronically. I however do recommend this book for its content as its brilliant. If you need to learn the mathematics side, then buy a book specific for that.

The quality of the book itself is really good. I also love the content.

It's a good book and reads well. It could use some formatting changes to make some of the content more digestible. But overall a great book.

Uno dei migliori libri in commercio di macchine learning, in particolare sul deep learning usando python e tensor flow.

Es un libro excelente, el autor explica conceptos complicados de una forma sencilla y entendible. Realmente hizo un gran trabajo de pedagogo, además estás aprendiendo del mismísimo autor de Keras, el framework más popular para machine learning. Eso sí, es importante tener conocimiento de programación y de conceptos matemáticos (cálculo, geometría, derivación, etc) ya que el Deep Learning es básicamente eso, pura matemática; vectores, matrices, operaciones vectoriales, espacios geométricos en varias dimensiones, etc. Cabe aclarar que el libro NO usa notaciones matemáticas; para darle sencillez, el autor decide usar en su lugar líneas de código que lo hacen mucho más digerible. Sin embargo, tener el conocimiento de estos conceptos te da el poder de entender lo que se está haciendo y de lo que se está hablando. PD: el libro en físico incluye todas las versiones digitales! Incluso Kindle!

Good book for Deep learning but one should know the basic knowledge of Numpy, Pandas and Data Visulaization and Machine Learning.