Introduction to Deep Learning
The course is part of this learning path
This Zero to Deep Learning course has been expertly created to provide you with a strong foundation in machine learning and deep learning. So whether you're just starting out with your practice of machine learning or you're a more experienced data scientist that is adding deep learning to the mix, this course will provide the necessary skills to serve as a solid foundation for you to continue learning after the course has been completed.
The course will start out covering simple data and structured data, then moving onto images, with sound, with text, and more complex data where deep learning comes to life. By the end of the course, you'll be able to recognize which problems can be solved with deep learning and organize data in a way that can be used by a neural network. Understanding and learning how to build a neural network model, including fully connected, convolutional, and recurrent neural network and train a model using cloud computing, all within this course.
This course is made up of 5 cohesive lectures that start off the journey into Data and Machine Learning with Cloud Academy.
- Learn the key principles of data and machine learning
- Come away with a strong foundation of the subject in order to develop new skills further
- Understanding and learning how to build neural network models
- No prior knowledge of data and machine learning required
Hello everyone. In this video, we're going to see how to download the course material and how to set up your laptop for the course. So let's start from the course material. In order to obtain the code for this course, you have to go to GitHub and point your browser to github.com/Dataweekends/zero_to_deep_learning_video. Once you reach our page, you will see the course repository. The instructions you're going to follow are detailed in the read me file of the video course. So all you need to do is just follow the instructions and you'll be up and running in no time.
The first thing you've got to do is to clone the repository on your laptop. So we are going to copy this command line here (
git clone https://github.com/Dataweekends/zero_to_deep_learning_video.git) which is 'git clone' and the URL of the course, and we're going to paste it into a terminal. If you are on Windows, you are going to do exactly the same thing. You're going to clone the repository, and you do that in the Anaconda Prompt that you will find if you have installed Anaconda. So we paste the same line in Windows and this will give us the same results.
Once we have downloaded the repository, of course we have already downloaded and installed Anaconda, so the next step is to change to the course folder and to create the environment. So I'll go ahead and do this on both machines, so I'll do this
conda env create on my Mac, as well as on Windows,
cd to zero_to_deep_learning_video, and then
conda env create.
While it's running, let me explain what's going on here. So we have provided in the repository an environment file which contains all the necessary packages for the course to run smoothly. So as you can see, it has a name, ztdl, which is the name of the environment, and a list of dependencies. All these dependencies come with Anaconda, so we have Python 3.6 and a set of libraries including scikit-learn and tensorflow.
We also installed keras, the most recent version, from pip, and that's why it's included as a pip dependency instead of an Anaconda dependency. Environment creation takes a few minutes, so give it the time to complete and come back to the video once the environment is created.
Once the environment is created, you should see these lines that say, "To activate this environment, use $ conda activate ztdl." On Windows, the same thing should appear, so it's exactly the same command as explained in the instruction. As you can see the next command is precisely
conda activate ztdl. So let's go ahead and do it,
conda activate ztdl, and you shall see that this changes your command prompt to
ztdl in parenthesis at the beginning. On Windows, exactly the same thing happens,
conda activate ztdl. This will change the command prompt to the ztdl environment. This tells us that we are running Python from within the ztdl environment that we have just created, which is a correct thing.
The next step in the instructions is to launch Jupyter notebook. So we'll go ahead and type
jupyter notebook in the command prompt. I'll do the same thing here,
jupyter notebook. This will start the notebook server in the backend as well as launch your browser. Once your browser opens, you will see that it opens to a page containing the content of the course repository. So you'll see all the folders you've cloned on your local environment replicated here, and all you've got to do is open the course folder and run the first notebook. On Windows, the same thing will happen, it should open your default browser and show you the course content. If you click on course, you can open the first notebook and get up and running.
If we open that 0_Check_Environment, this notebook performs a few checks and makes sure that you're running the notebooks from the correct environment. So what you're going to do is click on Cell, Run All, and if everything is done correctly, you should see that you're running Python 3.6 from within your environment folder you're running Jupyter, and this cell should evaluate to Houston we are go! That means that all the packages are in the correct major version.
If you see an error here, then go back to the read me and look at the Troubleshooting instructions. We've provided instructions for the most common failure modes including how to deactivate the environment, how to remove the environment, how to update conda, as well as instructions on how to run the course in a GPU-enabled environment. So make sure to check the read me and you'll be good to go.
This concludes the instructions on how to get the code and how to get your machine up and running. I'll see you in the next video.
I am a Data Science consultant and trainer. With Catalit I help companies acquire skills and knowledge in data science and harness machine learning and deep learning to reach their goals. With Data Weekends I train people in machine learning, deep learning and big data analytics. I served as lead instructor in Data Science at General Assembly and The Data Incubator and I was Chief Data Officer and co-founder at Spire, a Y-Combinator-backed startup that invented the first consumer wearable device capable of continuously tracking respiration and activity. I earned a joint PhD in biophysics at University of Padua and Université de Paris VI and graduated from Singularity University summer program of 2011.