IamSrutiJain

[iamsrutijain-blog]

Overcoming overplotting of Large Dataset: Data Visualization techniques

Overcoming overplotting of Large Dataset: Data Visualization techniques

Data visualization is an important aspect of any data analysis. Representation of information in the form of charts, diagram or picture provides valuable insight about the data including outliers, hot spots and missing data. Especially with large dataset where there are simply too many data points to examine each one, visualizations are helpful tools for understanding the properties of dataset.…

View On WordPress

[iamsrutijain-blog]

Balancing techniques for unbalanced datasets in Python & R

Balancing techniques for unbalanced datasets in Python & R

Data Samplingin data science is an important aspect for any statistical analysis project which is used to select, manipulate and analyze a representative subset of data points called samples in order to identify patterns and trends in the larger data set usually termed as population being examined. Lets say we are conducting a survey in the United States, and we collected data from 1000 samples.…

View On WordPress

[iamsrutijain-blog]

Monte Carlo Method - Data Analytics

Monte Carlo Method – Data Analytics

Monte Carlo Method is a computational mathematical technique that allows us to interpret all probable outcomes of our decisions allowing better decision making strategies under uncertainty. The essential idea behind this method is using randomness to solve problems that might be deterministic in principle.

During a Monte Carlo simulation, values are sampled at random from the input probability…

View On WordPress

[iamsrutijain-blog]

Machine Learning Datasets For Researchers/Data Scientists

Most important part of a research work is data, after all it is this data which formulates the entire research. Finding the most appropriate dataset is fundamental to success of any research, below…

[iamsrutijain-blog]

NIPS 2016 – highlight reel

The Thirtieth Annual Conference on Neural Information Processing Systems (NIPS) was a multi-track machine learning and computational neuroscience conference that included talks, demonstrations, sym…

[ucresearch]

A window into the brain

The Glass Brain is kind of like it sounds. It’s a colorful, 3-D window into all the mysterious activities that light up the brain. The technology lets you take a tour of your brain in real time.  

To create the animation, they overlay electroencephalography (EEG) data on a MRI scan.

It doesn’t just look cool. Neuroscientists are using the Glass Brain technology to study diseases like Alzheimer’s, autism and multiple sclerosis.

UCSF’s Adam Gazzaley developed the Glass Brain technology with a team at UC San Diego.

Jyoti Mishra, an assistant professor in the Gazzaley lab, utilizes this technology. She’s developing therapeutics for reducing attention deficit disorder in children.

Many of the startups emerging from the University of California have one thing in common: They aim to make the world a better place. Read more about the Glass Brain and other UC startups.

[yoursummerdreamz]

[iamsrutijain-blog]

Just love it! Beautiful

[iamsrutijain-blog]

Deep learning packages

Deep learning is a machine learning technique which models high level of abstraction through distributed representation. Having multiple layers, each preforming a transformation to input received f…

[iamsrutijain-blog]

Designing neural network: What activation function you plan to implement

Designing neural network: What activation function you plan to implement

Activation function defines the way the output is manipulated based on the input in a Neural Network. These functions must not only be differentiable but they are also mostly non-linear for determining a non-linear decision boundary using non-linear combinations of the input feature vector and weights. A few options for choosing activation function and their details are as under:

Identify…

View On WordPress

[iamsrutijain-blog]

What you need to know about data augmentation for machine learning — Cartesian Faith

What you need to know about data augmentation for machine learning — Cartesian Faith

Plentiful high-quality data is the key to great machine learning models. But good data doesn’t grow on trees, and that scarcity can impede the development of a model. One way to get around a lack of data is to augment your dataset. Smart approaches to programmatic data augmentation can increase the size of your training […]

via What you need to know about data augmentation for machine learning —…

View On WordPress

[iamsrutijain-blog]

Data Splitting in machine learning for high variance dataset

There are many factors that affect the performance of a machine learning model which is why we see different performance of different dataset on the same model. But what are these distinguishing factors. It is the way data is available and distributed. Data preprocessing is therefore one of the essential steps focused in the process of framing a learning model. It involves data cleaning,…

View On WordPress

[iamsrutijain-blog]

Are humans rational decision makers?

“If you’re rational you don’t get to believe whatever you want to believe.”  ― Michael Huemer

Difficult quote to understand when we first see it. Do we really believe it? Thinking upon it I realized that it is very much true.

Let’s say we are watching a cricket match, and Sachin Tendulkar have already hit four fours in the over. What’s your likely prediction of the next ball? Most of us will…

View On WordPress

[iamsrutijain-blog]

Watson Discovery Service – Cognitive application Reading the tech news today to find yet another new Watson innovation known as the "Watson Discovery Service" announced by IBM.

[iamsrutijain-blog]

How can extremly visualized clue effect cognitive function used for analysis : Astronomers think they’ve just discovered an ‘Interstellar’ black hole

Interesting, watching the video made me exited to find something like interstellar black hole being out there but it just raised a question as well. Spinning black hole like in the movie of interst…

[iamsrutijain-blog]

Artificial Life or the Alife, ethic concerns and what could we achieve?

What is artificial life? Artificial life as defined by Christopher Langton “Artificial Life is the study of man-made systems that exhibit behaviors characteristic of natural living systems. I…

[ucresearch]

A window into the brain

The Glass Brain is kind of like it sounds. It’s a colorful, 3-D window into all the mysterious activities that light up the brain. The technology lets you take a tour of your brain in real time.  

To create the animation, they overlay electroencephalography (EEG) data on a MRI scan.

It doesn’t just look cool. Neuroscientists are using the Glass Brain technology to study diseases like Alzheimer’s, autism and multiple sclerosis.

UCSF’s Adam Gazzaley developed the Glass Brain technology with a team at UC San Diego.

Jyoti Mishra, an assistant professor in the Gazzaley lab, utilizes this technology. She’s developing therapeutics for reducing attention deficit disorder in children.

Many of the startups emerging from the University of California have one thing in common: They aim to make the world a better place. Read more about the Glass Brain and other UC startups.

[iamsrutijain-blog]

Cross-sectional vs Longitudinal research design

Cross-sectional vs Longitudinal research design

Recently I am working on a project that urges me to review a lot of journal articles. Cross-sectional research and longitudinal research were one of the many things I came across. Below is just the very basic differences between the two that I learnt.

In cross- sectional researchwe don’t manipulate any variables, and we cannot make causal statements about the relationships between variables, so…

View On WordPress