Gain insights into advanced deep learning and NLP by building 12 real-world projects using tools like TensorFlow and scikit-learn. Enhance your portfolio with industry-relevant skills.

dockerfile.tar.gz

python3

spa-job

In this course, you'll not only learn advanced deep learning concepts, but you'll also practice building some advanced deep learning and Natural Language Processing (NLP) projects. By the end, you will be able to utilize deep learning algorithms that are used at large in industry.

 

This is a project-based course with 12 projects in total. This will get you used to building real-world applications that are being used in a wide range of industries. You will be exposed to the most common tools used for machine learning projects including: NumPy, Matplotlib, scikit-learn, Tensorflow, and more.

 

It’s recommended that you have a firm grasp in these topic areas: Python basics, Numpy and Pandas, and Artificial Neural Networks.

 

Once you’re finished, you will have the experience to start building your own amazing projects, and some great new additions to your portfolio.

Building Advanced Deep Learning and NLP Projects

# Problem one
***Build a model with `K = 6`, `K = 8` and `K = 10` and check the text generated.***

We will use the same code and functions that  we created in our previous lessons.

import numpy as np

# Generate the Lookup Table
def generateTable(data,k):  
  T = {}
  for i in range(len(data)-k):
    X = data[i:i+k]
    Y = data[i+k]
    if T.get(X) is None:
      T[X] = {}
      T[X][Y] = 1
    else:
      if T[X].get(Y) is None:
        T[X][Y] = 1
      else:
        T[X][Y] += 1
  return T

# Convert the Frequencies into Probability
def convertFreqIntoProb(T):     
  for kx in T.keys():
    s = float(sum(T[kx].values()))
    for k in T[kx].keys():
      T[kx][k] = T[kx][k]/s          
  return T

# Load the training data
def load_text(filename):
  with open(filename,encoding='utf8') as f:
    return f.read().lower()

# Create the Markov Chains
def MarkovChain(text,k):
    T = generateTable(text,k)
    T = convertFreqIntoProb(T)
    return T

# Perform Sampling
def sample_next(ctx,model,k):
    ctx = ctx[-k:]
    if model.get(ctx) is None:
        return " "
    possible_Chars = list(model[ctx].keys())
    possible_values = list(model[ctx].values())
    return np.random.choice(possible_Chars,p=possible_values)
  
# Generate the Text
def generateText(starting_sent,k ,maxLen):
    model = MarkovChain(text, k)
    sentence = starting_sent
    ctx = starting_sent[-k:]
    for ix in range(maxLen):
        next_prediction = sample_next(ctx,model,k)
        sentence += next_prediction
        ctx = sentence[-k:]
    return sentence
  
text = load_text("train_corpus.txt")
generated_text = generateText("dear my countrymen",k=8,maxLen=2000)
print(generated_text)

**Explanation:**
* We created the all the functions that we discussed in the previous lessons. One thing that has been changed is the default value of `K = 4` in every function. We removed this default value as for every different value of `K`, we need to generate a new Markov chain model.
* Run the above code with different values of `K` just by changing the value of `K` passed in the `generateText()` function.


# Problem two
***Take some other corpus of your own choice and generate the text.***

For this problem, we will use song lyrics. Below is a sample Indian song, which is in Hindi. You can take any other song lyrics of your choice.

In this lesson, we will discuss the solutions for the assignments in this chapter.

Welcome to the Course

Project: Build a COVID-19 Detection System Using X-Rays

Project: Building a Pokemon Classifier Using Transfer Learning

Project: Text Generation Using Markov Chains

Word Embedding: Two Mini Projects

Project: IMDB Reviews Sentiment Analysis

Project: Deciphering Text Using Character-Level RNNs

Project: Emoji Predictor Using Transfer Learning in NLP

Final Exam

Where to Go Next?

Assignment Solution

Problem one