Overview
Machine learning (ML), a subset of Artificial Intelligence (AI), is changing our lives at a much grander scale and in more ways than we can imagine. It is transforming the way things are done across sectors and industries, bit by bit. Natural Language Processing (NLP), another subset of artificial intelligence, is another technology contributing to this transformation.
Machine learning is a branch of AI that uses data and algorithms to imitate human actions and learn from the data to improve its accuracy. Deep learning is a subset of ML that works with algorithms and artificial neural networks that are inspired by the functioning of the human brain. Neural networks are another subset of ML that reflect how the human brain functions and are used to design computer programs that would recognize patterns and solve problems. Natural language processing is a branch of AI that enables computers to understand text and speech similar to how human beings could.
Together, these technologies are changing the world as we know it. Industries are embracing this new revolution by updating their processes and imbibing the wonders that these technologies can do. This has led to a huge surge in demand for professionals skilled in working with machine learning, deep learning, and natural language processing. All three of these technologies rank among the top ten skills to have for professionals every year. Keeping this huge demand in mind, Cognixia brings to you this machine learning online training to help individuals upskill in the field and make the most of this skills gap. This deep learning training is live, online, instructor-led with hands-on projects and assignments. This machine learning certification course covers important concepts like the fundamentals of Python, supervised and unsupervised ML algorithms, reinforcement learning, as well as fundamentals of NLP. Cognixia’s Machine Learning & Deep Learning, and NLP training & certification course will help participants learn all the essential skills and concepts to build a successful career in the field.
What You'll Learn
- Fundamentals of Python programming language
- Important libraries in Python and their applications
- Overview of machine learning
- Overview of statistics for machine learning & deep learning
- Supervised and unsupervised machine learning
- Reinforcement learning
- Overview of neural networks
- Fundamentals of Natural Language Processing
Curriculum
- Overview of Python
- Python Basics – variables, identifiers, indentation
- Data structures in Python – list, strings, sets, tuples, dictionary
- Statements in Python – conditional, iterative, jump
- Functions in Python
- Lambda functions
- Create arrays using NumPy
- Perform various operations on arrays and manipulate them
- Indexing, slicing and iterating
- Reading and writing data from text/CSV files into arrays and vice-versa
- Creating series and data frames in Pandas
- Data structures and index operations in Pandas
- Reading and writing data from Excel/CSV formats into Pandas
- Creating simple plots in Matplotlib
- Grids, axes, plots, markers, colors, fonts, and styling
- Types of plots – bar graphs, pie charts, histograms contour plots
- Choosing the right plot format for a problem at hand
- Scaling and adding style to your plots
- What is machine learning?
- Introduction to machine learning
- Types of machine learning
- Basic Probability required for machine learning
- Linear Algebra required for machine learning
- Measures of central tendency – Mean, Mode and Median
- Measures of spread – IQR, variance, and standard deviation
- Missing value treatment
- Outlier treatment
- Univariate and Multivariate analysis
- Inferential Statistics
- Hypothesis Testing – Type I and Type II errors
- P-value
- Level of Significance
- Confidence Interval
- Probability Basics and Conditional Probability
- Exploratory Data Analysis(EDA) – Practical use case
- Simple linear regression
- R2 and RMSE
- Logistic regression
- Decision trees
- Random forests
- SVM
- Naive Bayes
- Confusion Matrix
- Dimensionality reduction – PCA
- Cluster algorithms
- K-means Clustering
- Agglomerative Clustering
- Understanding reinforcement learning
- Algorithms associated with reinforcement learning
- Q-learning Model
- A Perceptron
- Neural networks
- Activation functions
- Deep learning with Keras
- Errors and Biases
- Back propagation
- Building your first neural network
- Building artificial neural networks (ANN) with Python (Model creation using TF/Keras)
- Computer vision – OpenCV
- Introduction to OpenCV – working with images
- Basics of NLP (Natural Language Processing)
- Removing Stop Words
- Stemming and lemmatization
- Parts of Speech Tagging
- TFIDF Vectorizer
- Sentiment Analysis
- SMS Spam Classifier
- Write the steps involved and develop the code to convert the data from the dataset of the above case study into a data frame. The data given includes details of all patients who were contracted with Pandemic from Nov 2019 and it is represented in the format of a .csv file. We must convert the file into a data frame to continue with further analysis.
- Analyzing the features, create a feature extraction analysis, considering the columns important for EDA. Manipulate only those columns which are important for visualization and the threatening scenario of the pandemic.
- Plot the data to understand the survival rate or mortality rate of the recent pandemic from the case study and the data given.
Prerequisites
FAQs
