How to get started in Deep Learning

By Al
Nowadays there are so many hot new technologies that is getting hard to sleep at night.

One of those technologies I have been recently looking into is Deep Learning. During the process I have come across some pretty good resources which are worth sharing. If DL is something you want to explore tune in. What I am recommending here can be done over a weekend. That investment will certainly not turn you into a seasoned Data Scientist but you will get enough to be dangerous. From the outside it looks like a harsh topic but what I have found is that when explained right it is not the "mission impossible" that looks from the outside

Deep Learning refers to the use of Neural Networks with several hidden layers. That's what make it "deep". So for me the logical place to start is Neural Networks, in particular try to understand the concepts. While trying to do just that I have come across this amazing channel in Youtube called “3Blue1Brown”. I don't know how else to spell it, is the most IMPRESSIVE channel I have ever seen. The quality of the videos is superb it is hard to describe. They have got a series of 4 videos explaining the theory or Deep Learning and Neural Networks. Their message is incredibly clear and the illustrations help heaps. Depending on how far you want to go you can watch the whole series or just watch the first one which is a "MASTERPIECE".



After that you will have enough background to enjoy a bit of play time with Tensorflow Playground. try a few scenarios for yourself.

https://playground.tensorflow.org


Then it is time to start tinkering by yourself. I would recommend Frank Kane TensorFlow series. I have bought some his courses under Udemy but he has published the Deep Learning videos for free in Youtube. He uses Python running on Windows to go through the whole thing. The course materials come in the form of Jupyter notebooks. They are a very common tool in the Data Science space. If you have never used them before don’t worry. In one of the videos Frank provides instructions on how to install Enthought Canopy


One thing you will soon discover is that a bit of Linear Algebra comes very handy when working in this field. If you need a quick refresher here is a good one I found:

https://towardsdatascience.com/linear-algebra-for-deep-learning-506c19c0d6fa

All in all is a very exciting field to get into. So if you have nothing else to do this weekend, I hope I gave you a few ideas

Enjoy!!

Comments

  1. Hema Yadav10 October, 2023 22:46

    Thanks for sharing your valuable thought and informative piece of content. Such a wonderful blog.
    Read my blog: Mastering of Python Script for System Administrator

    ReplyDelete

Post a Comment

Popular posts from this blog

Sending PowerStore alerts via SNMP

By Al
Image
In this previous article we discussed how to leverage PowerStore's powerful API to collect audit logs and send them to a Syslog server . We used Logstash to do that because of its extensive list of plugins Sometimes I come across organizations that still have a requirement to send storage array Alerts to SNMP. As in the Syslog case, ultimately most modern monitoring tools today support collecting information via REST API because that's the way the application world is going, i.e. the cloud native way ... it would be fun to see Prometheus monitoring Kubernetes via SNMP :) However there is still some requirement out there for SNMP traps, so we will explore how to do it. For simplicity we will use the same toolset that we used in the previous article. I encourage you to revisit quickly the article as we did an extensive introduction to Logstash, with practical examples as well as a description of the logs available in PowerStore. I won't cover those aspects in this article I
Read more

Electronic Nose - eNose

By Al
Image
In the previous article I provided details on VeeFarm which was one of the best projects we saw in ANZ Pied Piper 2019 edition and one of the best projects in the history of the program. The program inspired me and others to work together to showcase a great idea and the Pied Piper program itself during our presales conference. An idea I suggested to enhance VeeFarm was an electronic nose that could be used to detect the optimal ripening of the produce to advise the owner that it is the right time to pick it up the produce. This is an idea I had in the backburner for a while but never found the time to work on. Vee gave me the perfect excuse. The electronic nose, or eNose for short, is a custom PCB that hosts a range of gas sensors. For the proof of concept, I used the cheap MQ sensors. These are designed mostly for hobbyists and makers and they barely cost $1 per sensor. As one could expect, tweaking and calibrating these sensors it is even harder than the most expensive counter
Read more

Use Vagrant to deploy to AWS

By Al
Image
In the Pied Piper program we run through a Vagrant tutorial as we found it a great tool to help set up other labs. We are not going to cover Vagrant in detail in this blog as there are plenty of good examples out there. If you are interested in the exercises we did you can visit the repository: https://github.com/cermegno/vagrant-lesson However, something I felt is not sufficiently document and would make a good candidate for a post is how to use Vagrant to deploy to AWS and particularly from Windows. I found a couple of posts that provided good detail but none of them prevented me from running into Windows specific issues. If you are running it from Linux, this article will still help you as I will point out the differences anyway. Install prerequisites Firstly, as the Vagrant documentation states, "providers" other than VirtualBox require a plug in. This is how you install the AWS provider: vagrant plugin install vagrant-aws Deploying to AWS EC2 generally mea
Read more