IIM Bangalore’s DCAL workshops on Machine Learning using Julia and Natural Language Processing

Description

IIM Bangalore’s Data Centre & Analytics Lab to host workshops on Machine Learning using Julia and Natural Language Processing from July 16 to 18, 2021

Event Introduction

IIM Bangalore’s Data Centre & Analytics Lab (DCAL) will host workshops on Machine Learning using Julia and Natural Language Processing from July 16 to 18, 2021, from 09:30 am to 01:15 pm.

Please note that the last date for registration and payment for the workshops is July 03, 2021. Participants will be provided e-certificates after completion of the event.

Due to current restrictions on crown gatherings, the workshops will be hosted on the virtual platform.

The DCAL at IIMB has been set up to support interdisciplinary empirical research using data on primarily Indian as well as other emerging markets. The vision of this initiative is to be India’s most comprehensive research data source.

Topics to be Covered

📌 Machine Learning using Julia Click here for course content

Day 1: Understanding Anaconda Framework platform and other useful packages in Julia
Session 1–Introduction to Business Analytics
• What is Business Analytics – Tools, Techniques, Context
• Why is it needed and how industries are adopting it
• Different components of analytics – Descriptive, Predictive and Prescriptive
• Different types of machine learning algorithms–Supervised and Unsupervised learning
Session 2 & 3–Introduction to Anaconda and Julia
• Overview of Jupyter Notebook
• Julia – Variables, objects, loops, conditions, function.
• Julia Data structures – lists, tuples, dictionaries, sets
• Overview of Data Analysis Stack – DataFrames.jl, CSV.jlSeaborn, Plots.jl, GLM.jl, GLMNET.jl, MultivariateStats.jl, ScikitLearn.jl
Day 2: Understanding regression and its implementation using Julia
Session 1–Data Exploration and visualization
• Loading data from Files
• Data manipulation – Filtering, Grouping, Ordering of data
• Dealing with missing Data
• Drawing Histograms, Bar charts, Scatter Plot, Box Plots
• Understanding Basic Statistics, Distributions, Correlations
Session 2 & 3–Lab 1: Linear Regression
• Understanding Regression and Examples
• Understanding loss function and gradient descent
• Building Linear Regression Model
• Creating Training, validation and Test Data Sets, Cross validations
Day 3: Understanding logistic regression and its implementation using Julia
Session 1–Lab 1: Linear Regression
• Understanding Evaluation Metrics: RMSE, R-square
• Case study using regression techniques and hands-on using Julia code for regression
Session 2&3–Lab 2: Logistic Regression
• Understanding Classification and Examples
• Introduction to Logistic Regression, strategy to find the optimal cut-off
• Loss function and regularization
• Understanding Evaluation Metrics: Confusion Matrix, Precision, Recall, Accuracy etc

📌 Natural Language Processing Click here for course content

Day 1:
Introduction to NLP and its components: Natural Language Understanding (NLU), Natural Language Inference (NLI) and Natural Language Generation and its Applications
NLP pipeline – pre-processing steps, data normalization, vectorization/encodings Understanding the concept of Embeddings and its advantages over other encodings;
Properties of Embeddings; GloVe and Word2Vec (CBOW and Skip-gram); Transfer learning
Day 2:
Sequential models/architecture: Convolution 1D and Recurrent Neural Networks
(RNNs)
RNN Architectures – Long-short Term Memory (LSTM), Gated Recurrent Units (GRU), Stacked RNNs, Bi-directional RNNs
NLP Applications: Sentiment Analysis (with masking), Named Entity Recognition, Language Modeling – character prediction model;
Day 3:
Encoder-Decoder model, Attention Mechanism, Transformers
Sub-word encoding: Byte-pair encoding, WordPiece encoding
Deep Contextualized word representations – ELMo (Embeddings from Language Models), BERT (Bi-directional Encodings Representation from Transformers)- FineTuning Overview of various models – ULMFiT (Universal Language Modeling Fine-Tuning),
Generative Pre-Training (GPT)
NLP Applications: Machine Translation, Fine-Tuning/Text Classification using BERT.

Who Should Attend

Irrespective of type of industry (retail, e-commerce, manufacturing, real estate & construction, telecom, hospitality, banking, healthcare, IT, supply chain &logistic, etc.); data forms the crux of decision making. This course is designed for graduates and post graduates who will venture into the corporate set up and will be assisting the management in various decision making process. This course is equally suited to hone up analytical skills and business acumen of midlevel and senior level corporate professionals trying to understand the nuances of data science and help them the machine learning techniques an efficient way to generate insights
for customers which in turn optimizes the bottom line of organizations.

Registration Fee

◆ INR 5000 (Inclusive of GST at 18%)

How to Apply

◆ Candidate should submit an online application by clicking the Apply Online. Participants need to fill up the online application form by using the link given below with all the required details.

E-Certificate will be provided post the event.
IIMB reserves the right to alter the content at its sole discreation
Use the below links to Register/ Login & make Payment
http://dcal.iimb.ernet.in/BAI_Symposium_2021/workshops.php

Important Date

• Last date for registration is 03 July, 2021
• Event date  16 to 18 July, 2021

For Additional Information

IIM Bangalore’s Data Centre & Analytics Lab to host workshops on Machine Learning using Julia and Natural Language Processing from July 16 to 18

Organizer Information 🇮🇳

Indian Institute of Management Bangalore,
Bannerghatta Road, Bengaluru, India
Pin Code : 560076

Highlights

• Workshops  on Machine Learning using Julia and Natural Language Processing Organized by Indian Institute of Management Bangalore
• Learn About Machine Learning using Julia and Natural Language Processing
• Workshops Programme for Faculties/ research scholars/ PG students and Industry employees