HomeDeep LearningAndrew Ng Deep Learning Specialization: Best Deep Learning Course for Beginners and Deep Learners
Deep Learning Specialization on Coursera

Andrew Ng’s Deep Learning Specialization has launched before August 15, 2017, and everyone can enroll it by Coursera and learning the Deep Learning Course free for seven days and then cost 49 dollars per month. I have enrolled the deep learning specialization last Saturday, and finished the first course of the Depp Learning Series: Neural Networks and Deep Learning, include the course videos, quizs, and programming assignments, feel very good.

Master Deep Learning and explore the frontier of AI with Andrew Ng’s highly anticipated Deep Learning Specialization. Only on Coursera.

Specifically, the difficulty of this deep learning course has been lowered by Andrew Ng, and like his Machine Learning course, this is a deep learning course for AI beginners and developers and deep learners:

If you want to break into AI, this Specialization will help you do so. Deep Learning is one of the most highly sought after skills in tech. We will help you become good at Deep Learning.

In five courses, you will learn the foundations of Deep Learning, understand how to build neural networks, and learn how to lead successful machine learning projects. You will learn about Convolutional networks, RNNs, LSTM, Adam, Dropout, BatchNorm, Xavier/He initialization, and more. You will work on case studies from healthcare, autonomous driving, sign language reading, music generation, and natural language processing. You will master not only the theory, but also see how it is applied in industry. You will practice all these ideas in Python and in TensorFlow, which we will teach.

You will also hear from many top leaders in Deep Learning, who will share with you their personal stories and give you career advice.

AI is transforming multiple industries. After finishing this specialization, you will likely find creative ways to apply it to your work.

We will help you master Deep Learning, understand how to apply it, and build a career in AI.

The organization of the Deep Learning Specialization is very professional:

The Deep Learning Course is not only for AI beginners, but also for deep learning users. Based on the actually course experience, I strongly recommended the deep learning course for you, the value of the course is more than you pay.

The first course of the Deep Learning Specialization is “Neural Networks and Deep Learning“, which include four parts:

1. Introduction to deep learning
2. Neural Networks Basics
3. Shallow neural networks
4. Deep Neural Networks

The first week course is about “Introduction to deep learning”, no programming assignment, just quiz, very simple:

The second week course “Neural Networks Basics” start with Binary Classification, then Logistic Regression, Gradient Descent, and Computation Graph:

The second week deep learning basic course provides the programming assignments with a basic python video course: Python and Vectorization. You should use Python to finish the course programming assignments with online Jupyter Notebook provides by Coursera, very convenient. The course focused on Vectorization, and use Numpy tools mainly:

The best part of the Deep Learning Course certainly is the design of the programming assignments, first provides an optional programming assignment: Python Basics with numpy (optional), then the related programming assignment: Logistic Regression with a Neural Network mindset. Most part of the code has finished by teacher, you just need write few lines of key part:

The third week course is about “Shallow neural networks”, I’m most concerned about the Backpropagation , but actually, I’m not satisfied about the introduction about the Backpropagation by Andrew Ng. But other videos such as activation function, random parameter initialization are very excellent:

And especially, the programming assignment for this week is perfect. In Python Notebook, the programming assignment tell you everything about the basic concept of a neural network. It was a classic case of “hand in hand to teach you to write a neural network in Python step by step”:

The last week course of the “Neural Networks and Deep Learning” is about Deep Neural Networks, based on the previous course, the video course the fourth week is relatively simple:

And still, the programming assignments for this week are very cool, one is about “Building your Deep Neural Network: Step by Step”, another is bout “Deep Neural Network Application”:

This is my final grades of the first course of the Deep Learning Specialization

After finished it, I can not wait to get into the next deep learning course by Andrew Ng: Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization

Master Deep Learning and explore the frontier of AI with Andrew Ng’s highly anticipated Deep Learning Specialization. Only on Coursera.

Posted by Text Miner

Deep Learning Specialization on Coursera


Andrew Ng Deep Learning Specialization: Best Deep Learning Course for Beginners and Deep Learners — 3 Comments

  1. I have no experience in these fields . Can these courses is for zero in these fields. I want to explore and make career in these field but till now I am iOS developer. No experience in machine learning or deep learning or ai not data science. Please guide me.

      • Sir i want to upload my assignments guide me what i have to upload in .json file…

        **Exercise**: Using your code from “Python Basics”, implement `sigmoid()`. As you’ve seen in the figure above, you need to compute $sigmoid( w^T x + b) = \frac{1}{1 + e^{-(w^T x + b)}}$ to make predictions. Use np.exp().

        # In[37]:

        Sir which part of code i have to upload or save in my .json file to upload in submission area of assignment….

        # GRADED FUNCTION: sigmoid

        def sigmoid(z):
        Compute the sigmoid of z
        z — A scalar or numpy array of any size.
        s — sigmoid(z)

        ### START CODE HERE ### (≈ 1 line of code)
        s = 1 / (1 + np.exp(-z))
        ### END CODE HERE ###

        return s

        # In[38]:

        print (“sigmoid([0, 2]) = ” + str(sigmoid(np.array([0,2]))))

        # **Expected Output**:
        # **sigmoid([0, 2])**
        # [ 0.5 0.88079708]

Leave a Reply

Your email address will not be published.