Planning to do some deep learning course sessions e.g. fastai , google ML crash course etc. Also try to understand common tools (tensorflow, jupyter notebook, numpy, pandas, pytorch) and practices e.g. Convoluation neutral nets, SGD used to solve learning problems.
Aim is to get ready for kaggle competition (https://www.kaggle.com/competitions) eventually to test out learning and develop intuition around categories of learning problems.
http://course.fast.ai/ ( useful links for setting us GPU server env in AWS for this course ..
http://forums.fast.ai/t/aws-ami-available-for-testing/7255
https://towardsdatascience.com/setting-up-and-using-jupyter-notebooks-on-aws-61a9648db6c5
https://developers.google.com/machine-learning/crash-course/
Intro to Pandas https://colab.research.google.com/notebooks/mlcc/introtopandas.ipynb?utmsource=mlcc&utmcampaign=colab-external&utmmedium=referral&utmcontent=pandas-colab&hl=en
TensorFlow: Install Tensorflow https://www.tensorflow.org/install Download models https://github.com/tensorflow/models.git TensorFlow tutorial: https://www.youtube.com/watch?v=yX8KuPZCAM
Looking for hackers with the skills:
Nothing? Add some keywords!
This project is part of:
Hack Week 17
Comments
-
over 6 years ago by riafarov | Reply
Hey! There are deep learning AMIs in AWS, I've used them for my experiments with CUDA: https://aws.amazon.com/blogs/machine-learning/get-started-with-deep-learning-using-the-aws-deep-learning-ami/ It's possible to run them on micro instance, so only storage will be chargeable
-
over 6 years ago by arun_kant | Reply
Yes, I have been using these AMIs in AWS with spot instances in US east AZ. These AMIs helps a lot in rebuilding with new spot instances and have some chargeable storage for configuration.
Thanks for sharing the information.
Any other tooling or specific material you find interesting for learning deep learning?
-
Similar Projects
This project is one of its kind!