Class Central is learner-supported. When you buy through links on our site, we may earn an affiliate commission.

Kadenze

Creative Applications of Deep Learning with TensorFlow

via Kadenze

Overview

This first course in the two-part program, Creative Applications of Deep Learning with TensorFlow, introduces you to deep learning: the state-of-the-art approach to building artificial intelligence algorithms. We cover the basic components of deep learning, what it means, how it works, and develop code necessary to build various algorithms such as deep convolutional networks, variational autoencoders, generative adversarial networks, and recurrent neural networks.

A major focus of this course will be to not only understand how to build the necessary components of these algorithms, but also how to apply them for exploring creative applications. We'll see how to train a computer to recognize objects in an image and use this knowledge to drive new and interesting behaviors, from understanding the similarities and differences in large datasets and using them to self-organize, to understanding how to infinitely generate entirely new content or match the aesthetics or contents of another image.

Deep learning offers enormous potential for creative applications and in this course we interrogate what's possible. Through practical applications and guided homework assignments, you'll be expected to create datasets, develop and train neural networks, explore your own media collections using existing state-of-the-art deep nets, synthesize new content from generative algorithms, and understand deep learning's potential for creating entirely new aesthetics and new ways of interacting with large amounts of data.



What students are saying:


"It was a fantastic course and I want to say "super big thank you" to the instructor Parag Mital. His lectures were highly valuable and inspiring. It not only gave me inspiration in how to apply ML for art, it gave me deeper insights in Deep Learning in general."


"After taking several courses in Machine Learning, I came across this course and it immediately caught my attention due to the the speed of delivery, content topics and it's pace when talking about concepts such as gradient descent and convolutions. Honestly, the course truly is EXCELLENT. Parag really is great a presenting the materials in an easy-to-understand manner, and perhaps more importantly, he has you focus on the RIGHT concepts and not going down rabbit-holes."

Syllabus

  • Introduction to TensorFlow
    • We'll cover the importance of data with machine and deep learning algorithms, the basics of creating a dataset, how to preprocess datasets, then jump into Tensorflow, a library for creating computational graphs built by Google Research. We'll learn the basic components of Tensorflow and see how to use it to filter images.
  • Unsupervised And Supervised Learning
    • We explore deep neural networks capable of encoding a large dataset, and see how we can use this encoding to explore "latent" dimensions of a dataset or for generating entirely new content. We'll see what this means, how "autoencoders" can be built, and learn a lot of state-of-the-art extensions that make them incredibly powerful. We'll also learn about another type of model that performs discriminative learning and see how this can be used to predict labels of an image.
  • Training A Network W/ TensorFlow
    • We'll see how neural networks work, how they are "trained", and see the basic components of training a neural network. We'll then build our first neural network and use it for a fun application of teaching a neural network how to paint an image, and explore such a network can be extended to produce different aesthetics.
  • Generative Models
    • The last session offers a teaser into some of the future directions of generative modeling, including some state of the art models such as the "generative adversarial network", and its implementation within a "variational autoencoder", which allows for some of the best encodings and generative modeling of datasets that currently exist. We also see how to begin to model time, and give neural networks memory by creating "recurrent neural networks" and see how to use such networks to create entirely generative text.
  • Visualizing And Hallucinating Representations
    • This sessions works with state of the art networks and sees how to understand what "representations" they learn. We'll see how this process actually allows us to perform some really fun visualizations including "Deep Dream" which can produce infinite generative fractals, or "Style Net" which allows us to combine the content of one image and the style of another to produce widely different painterly aesthetics automatically.

Taught by

Parag Mital

Reviews

4.7 rating, based on 45 Class Central reviews

Start your review of Creative Applications of Deep Learning with TensorFlow

  • Profile image for Gabriel Montagné
    Gabriel Montagné
    This is a great course -- the approach is quite unique compared to other Deep Learning courses as it is geared, from the outset, to doing creative work: visualisations, image processing, and generation. Funnily, this actually helps to understand th…
  • Anonymous
    Very high quality materials and video. with interesting subject matter. I was looking more for a course introducing working with TensorFlow. I have a deep CS background but limited ML exposure/experience. The sessions started out with a very good balance between hands on development, explanation, and theory, but I felt the Tensor flow aspect of the explanation facet started going down the further into the sessions you got. Too many instances for: "here is some code to run but I don't have time to explain it". I really think you should have spent some time on TensorBoard if a good portion of the code you were walking through in Session 5 was there to integrate with it.
  • Anonymous
    Fun and insightful combination of learning TensorFlow with example applications using neural networks for image analysis, visualisation plus generating text and music.

    The course presents a minimal amount of theory, and has a hands-on approach. A typical session involves building and running a basic deep network for a task using TensorFlow commands (in Python on Jupyter notebook), getting a feel for what that does, then a guided use of a more advanced model. Assignments start with a 90% complete notebook, with gaps to fill and parameters to adjust.
  • Anonymous
    The instructor seems very active on the forums and even set up a slack for the course. It's been great, and the homework and notebooks are really easy to follow. So far it has really made me think and seems a lot more engaging than the Udacity or Coursera course. Can't wait to see where it goes!
  • Profile image for Sergio Marchesini
    Sergio Marchesini
    I think this course is excellent and inspiring. The teaching material is very good and the quality of the lessons is high. Just one note: it's not easy, if you are new to Machine Learning it will take a lot of time and CPU. But it will be worth it!
  • Anonymous
    This is a very hard course! But this is also a very hard subject matter. It is amazing to see this course geared towards Creative applications. Very well produced course. Probably one of the best I have seen online
  • Anonymous
    Fantastic course, moves very fast, huge learning curve, non programmers might struggle, be prepared for a lot of reading, the instructor is 1 on 1 with every student in the forums, when you finish you will realize you have entered a new universe of possibilities.
  • Anonymous
    In 1st session right now! But this course seems very different to other tensor flow course I took from udacity! Session 2 and 3 look amazing!
  • Profile image for Rates
    Rates
    This course has decent content, but the pedagogy is pretty unpolished in my opinion. Parag doesn't spend enough time convincing the student WHY they should care about what they are doing or provide enough context of where this material is situated i…
  • Anonymous
    This course is really great to learn TensorFlow and manipulate advanced net architectures, like VAE/GAN. The explanations of Parag are great. The code provided for the assignments is just outstanding and is definitively valuable after the course. I need to point out that the community around the course is really active. I had the opportunity to discuss with real creative people, which I have highly appreciated.
  • RahmanUddin
    This is the course I was looking forward to enrol in to. DNN Implementation in various environments. Very supportive forum plus detailed instructions and on screen examples. Hard to resist to start next session, but I must say, I am taking one step at a time and first practising whats being taught and then moving onto to next session. Though you might be missing a smile on the face of such nice tutor, but never the less lost of love and respect.
  • Excellent course for anyone without a technical background interested in harnessing the power of Machine Learning for their creative projects. The material is very well organised building up on practical examples and comes with great support from Parag. It has been immensely helpful for my own work and I highly recommend it!
  • Anonymous
    I started taking this course and the most amazing part is being able to see the student work in the gallery. I can't believe that machine learning can result in images like this! I hope I am smart enough to be able to accomplish this myself. I also see that there is now a Part II and Part III of this course! Lots to learn.
  • Profile image for Varun Raj
    Varun Raj
    Best course to learn tensor flow. You need have a good understanding of NN theory before starting this class. Otherwise you will feel lost very soon. Do Andrew NG's Machine Learning till week 5 and get to this course to get a good grasp of material.

    Overall, great course !!
  • As I had already earned the certificate, I think this course is a great one. We have here all necessary tools to understand, master and go deeper in the domain of Deep Learning with Tensorflow.
  • Anonymous
    So far, it is clearly the best tensorflow course I have seen. The instructor is very competent, the course material is well-designed and extensive, the quality of the videos and the english pronounciation is perfect.
  • Anonymous
    Excellent content. The course is very neatly designed and has been presented in an appropriate manner. The course gradually moves from the core foundations to the applications of tensorflow. Parag has done an excellent job in putting forth all advanced concepts. Highly Recommended !

    -Prateek Katageri
  • Anonymous
    The first session has been superb. The approach the instructor is taking is really good. I've paid for a certificate. Excited for the remaining sessions!
  • Anonymous
    Very technical, very informative, really good analysis of the deep learning approaches. The excercises after each lecture are very useful for gathering some hands-on experience. Can't recommend enough :)
  • Anonymous
    I learned so much! It's a fascinating course and I'd recommend it to anyone curious about AI or what is possible with it. It's not an easy course especially towards the end but gives you plenty to think about.

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.