Follow

Bishal Lakha

AI and Physics Enthusiast. Robotics Teacher. Previously worked at Coursera.

Tutorials

Discussion

Comments

Followers

Course Completions

Active In

Data Science and Big Data

1 reply. Member

Reading

Member

Quantum Computing

Member

Deep Learning

1 reply. Member

Competitive Programming

Member

Deep Learning Book

Member

Big Data

1 discussion. Member

Featured Contributions

NaN.

tutorial

An Overview of Data Scienceby Wiki

Welcome to your first Data Science Tutorial on CommonLounge. This tutorial will be quite different from the rest of the tutorials in this course, and will give you a broad overview of the field of data science.

What is Data Science? ...

Read more…(1594 words)

Category: Data Analytics

comment in this discussion

Bishal LakhaAI and Physics Enthusiast. Robotics Teacher. Previously worked at Coursera. · 1y

You can check the estimates in the graph provided in the tutorial.

Read more… (12 words)

NaN.

tutorial

Statistics: Central Tendency metrics, Dispersion and Correlationby Wiki

Introduction

Statistics is a very broad branch of mathematics tha...

Read more…(1132 words)

Category: Data Analytics

comment in this discussion

Bishal LakhaAI and Physics Enthusiast. Robotics Teacher. Previously worked at Coursera. · 1y

Best wishes

Read more… (2 words)

NaN.

course

Learn Data Science with Pythonby Keshav Dhandhania

Overview

This 45-part course consists of tutorials, quizzes, hands-on assignments and real-world projects to learn data science, as well as advanced python tools for data science.

Key Features of the Co...

Read more…(355 words)

Category: Data Science and Big Data

comment in this discussion

Bishal LakhaAI and Physics Enthusiast. Robotics Teacher. Previously worked at Coursera. · 2y

Most of the tutorials are self sufficient. But you should have some knowledge of Python to understand some project based tutorials like Predicting Titanic Survivors with Machine Learning.

Read more… (28 words)

NaN.

tutorial

Linear Algebra: Vectors, Matrices and their propertiesby Wiki

Introduction

Large datasets are often comprised of hundreds to mi...

Read more…(1048 words)

Category: Machine Learning

comment in this discussion

Bishal LakhaAI and Physics Enthusiast. Robotics Teacher. Previously worked at Coursera. · 2y

Hi Somto, this is a good place to begin learning Data Science :)

Read more… (13 words)

Contributed 100%

6.

tutorial

Speech Recognition with Weighted Finite-State Transducers: Paper overview

Back in 2007-2008 Mehryar Mohri ,Fernando Pereira and Google researcher Michael Riley, were developing speech recognition system based on Weighted Finite State Transducer.The transducer proposed by them provided a common and natural representation for major components of speech recognition systems, including hidden Markov models (HMMs), context-dependency models, pronunciation dictionaries, statistical grammars, and word or phone lattices.[1]

A finite-state transducer is a finite automaton whose state transitions are labeled with both input and output symbols while a weighted transducer puts weights on transitions in addition to the input and output symbols.[1] The examples in Figure 1(a) [1, Fig.1] represents the language model used for speech recognition by giving each transition identical input and output labels. This language model predicts how probable particular sentence over other. For example, if the first is ‘using’ (having probability of occurrence 1) then the word following it can be either ‘data’ with probability of occurrence 0.66...

Read more…(973 words)

Category: Machine Learning

Contributed 100%

7.

tutorial

Domain Adaptive Faster R-CNN for Object Detection in the Wild: Paper Overview

Main idea

Problem Statement

When training and test data are drawn from different distribution, performance of traditional object detection model drops significantly.

2. Proposed Solution

Domain Adaptive Faster R-CNN model can be used to effectively detect object from cross domain. Domain variation might be the result of difference in camera type, different weather condition, difference in appearance ,image quality, backgrounds etc. Following variations were considered here:

Image level variation like image style, illumination etc
Instance level variation like appearance,size etc

Resources

Read more…(386 words)

[1803.03243v1] Domain Adaptive Faster R-CNN for Object Detection in the Wild

http://arxiv.org/abs/1803.03243v1

Category: Deep Learning

NaN.

tutorial

An Overview of Data Scienceby Wiki

Welcome to your first Data Science Tutorial on CommonLounge. This tutorial will be quite different from the rest of the tutorials in this course, and will give you a broad overview of the field of data science.

What is Data Science? ...

Read more…(1594 words)

Category: Data Analytics

comment in this discussion

Bishal LakhaAI and Physics Enthusiast. Robotics Teacher. Previously worked at Coursera. · 2y

It depends on your need. For example if you want to use cutting edge statistical methods , R is a better options while Python is better when you want to build a scalable product. These articles will help you understand it better:

Read more… (57 words)

NaN.

tutorial

End-to-End Example: Using Logistic Regression for predicting Diabetesby Wiki

In this tutorial, we will see how to predict whether a person has diabetes or not, based on information like blood pressure, body mass index (BMI), age, etc.

The data was collected and made available by "Nation...

Read more…(1617 words)

Category: Machine Learning

comment in this discussion

Bishal LakhaAI and Physics Enthusiast. Robotics Teacher. Previously worked at Coursera. · 2y

Hello Shaurya, you can use the notebook along the tutorial. The best way to learn is by doing. Play with the note book, learn what those code is doing from the tutorial , post questions if you find any portion difficult to follow. In that way you will get best out of this tutorial :)

Read more… (55 words)

NaN.

tutorial

End-to-End Example: Using Logistic Regression for predicting Diabetesby Wiki

In this tutorial, we will see how to predict whether a person has diabetes or not, based on information like blood pressure, body mass index (BMI), age, etc.

The data was collected and made available by "Nation...

Read more…(1617 words)

Category: Machine Learning

comment in this discussion

Bishal LakhaAI and Physics Enthusiast. Robotics Teacher. Previously worked at Coursera. · 2y

Feature bucketing is a feature engineering technique in which we convert continuous values of some feature ( for example age) to fixed ranges ( like 10-15, 15-20). This technique proves helpful in reducing noise endured by machine learning algorithms resulting in enhanced performance. You can explore the idea further in this blog :

Creating Buckets or Clusters for Numeric Column Values in Exploratory

Read more… (63 words)

NaN.

Q&A session

Q&A Session with Kirk Borne (Principal Data Scientist, Booz Allen Hamilton)by Kirk Borne

Data Scientist. Public Speaker. Consultant. Astrophysicist. Space Scientist.

Big Data & Data Science advisor, TedX speaker, c...

Read more…(213 words)

Category: Data Science and Big Data

comment in this discussion

Bishal LakhaAI and Physics Enthusiast. Robotics Teacher. Previously worked at Coursera. · 2y

Hello Kirk, which area of research do you think needs immediate attention for advancement of machine learning/ data science?

Read more… (19 words)

Load More