- +91-9602880219, +91-8104464971, +91-78520716531
- info@regexsoftware.com
Menu
(Batches Start from 1st & 8th Mar, 2021)
About The Program:
With the belief to build a healthy ecosystem as per the Industry Standards REGex Software brings a Internship/Training Program on “DataScience – Machine Learning & Deep Learning”. We organize Internship/Training Program for improving the knowledge and skills of the Students/Professionals, so that they can become expert in Machine Learning and get their Dream Job in Software Development Field in Big MNCs.
REGex Software Services’s “DataScience – Machine Learning & Deep Learning” course is a valuable resource for beginners and experts. This course will introduce you to Classification, Clustering Algorithm and Working on Object Detection & Image Recognition from Basics to Advance. If you are preparing for a coding interview, REGex introduce this course for you.
Best affordable Python + Django program with live classes and doubt solving. You can also access to recordings of the classes. Teachers and mentor are very good. All syllabus covered in given time. With multiple live examples. Best part of training is friendly environment. Don't hesitate to enroll if you've never heard the name of this company before. You will not be disappointed.
Competitive Programming is the best course they have - i am part of both python and C++ course. Cracked several interviews with their course, poll test & assignment are always new and beneficial. Best CP course you will find here, i hope this will be beneficial for you
Tushar sir is best in delivery. His approach is mind blowing. I have not found any gap although I am from U.S Lots of Big Data tools I have learnt like Hadoop, Hive, Spark, Sqoop & most amazingly Talend ETL Tools which was the most lovely part of training. every component is told in very simple terms with great practical approach
I recently joined Python Django(Web Development - Full Stack)Course About Course: - I must say instructor makes every concept simple to understand - No Copy Paste,Every line of code is explained - Even given Assignments to work on - Even given Projects to work on If you looking to learn Python Django I highly recommend to go for this course
I am from UK & loved the teaching. Competitive Programming was the best experience I had in coding. I can truly say the money I spend is worth it. Go for it guys!!
24*7 Mentorship Support
Working on Live Projects
Live Sessions by Expertise Trainers and Access of Recorded Session is also available
Get a chance to work on Industry Oriented Projects to implement your learning
24*7 Mentorship Support available for all Students to clear all of your doubts
REGex provides Internship / Job opportunities to the best Students in different Companies.
S. No. | Topic |
|---|---|
1 | Machine learning |
○ Machine learning applications ○ ML vs DL | |
2 | Data Cleaning & Munging with – Python
|
○ Basics of Python [Syntax] ○ Working with Pandas, Numpy & Matplotlib ■ Working with Missing Data ■ Data Grouping ■ Data Subsetting ■ Merging & Joining Data Frames ○ Importing Libraries & Datasets ○ Munging & handling missing data ○ Splitting the dataset into Training set & Test set | |
3 | Understanding all concepts of Machine
Learning
|
○ What is actual machine learning ○ Various Aspects of Data – type, Variables & Category ○ Machine Learning & its Various types | |
4 | Supervised & Unsupervised machine Learning |
5 | Understanding with Simple Linear Regression |
6 | Multiple Linear Regression Intuition |
○ Understanding the P -Value | |
7 | What is Regression with its use cases |
○ Support Vector Regression | |
8 | Decision Tree Regression & Random forest
Regression |
9 | Logistic Regression |
○ K-NN [K-Nearest Neighbors] | |
10 | Support Vector Machines |
11 | Bayes Theorem |
○ Naive Bayes Intuition | |
12 | Dimension Reduction & Feature Selection |
○ Principal Component analysis (PCA –
Theory) ○ PCA with Case-Study ○ Linear Discriminant Analysis(LDA) for Dimension Reduction ○ Feature Selection to Select the Most Relevant Predictors | |
13 | Evaluating classification models performance |
○ Confusion matrix ○ Accuracy Paradox ○ CAP Curve | |
14 | K-Mean Clustering |
○ K-Mean Clustering Intuition ○ K-Mean selecting Numbers of Cluster | |
15 | Reinforcement learning |
16 | Traditional A/B Testing |
17 | NLP |
○ NLP Intuition ○ Types of NLP ○ Classification vs Deep Learning Models |
S. No. | Topic |
|---|---|
18 | Understanding about Deep Learning |
○ The Neuron ○ Activation function ○ How Neural network work & learn by itself ○ Gradient Descent ○ Stochastic Gradient Descent ○ Ethics of Deep Learning | |
19 | Deep Dive with ANN |
○ What are convolutional neural networks
[CNN] ? ○ CNN Architecture ○ CNN Code preparation ○ Recurrent Neural Networks ○ Several layers ■ ReLLu Operation ■ Pooling ■ Flattering ■ Full Connection | |
20 | Statistics and probability Refresher |
○ Learn about mean, median, mode ○ Variation ○ Standard Deviation ○ Density Functions ○ Probability Mass function ○ Percentiles ○ Covariance & Correlation | |
21 | Computer Vision & OpenCV |
○ What is computer vision & its
application ○ Face Detection ■ Adding more features & Categorization ■ Object Detection ■ Image creation ■ Working with Images ■ Working with Vectors ○ Facial Expression Recognition in Code (Binary / Sigmoid / Logistic Regression) | |
22 | Natural Language Processing [ NLP] |
○ What are Vectors ○ Working with word Analogy ○ Text Classification ○ Pre Trained word vectors from word2vec ○ Language Models | |
23 | TensorFlow / Keras |
○ Introduction to Tensorflow / Keras ○ Most used right now ○ Resources gathering ○ Keras dealing with Missing Data ○ Dealing with Categorical data | |
24 | AWS SageMaker |
○ Create your own ML models ○ Deploy ML models ○ AWS Rekognition | |
25 | Capstone Project |