Blog – Nipun Batra Blog

Categories

All (112)

academia (2)

adagrad (1)

adversarial-networks (1)

air quality (1)

algorithms (2)

approximate-inference (1)

attention-mechanism (2)

audio (1)

automated-machine-learning (1)

automation (1)

automl (1)

bayesian (5)

clustering (1)

collaborative-filtering (1)

computer vision (1)

computer-vision (1)

data visualization (1)

data-aggregation (1)

data-analysis (2)

data-science (1)

data-visualization (1)

deep learning (3)

deep-learning (6)

denoising (1)

development-environment (1)

digital-signal-processing (1)

dimensionality-reduction (1)

distance-metrics (1)

dynamic-time-warping (1)

expectation-maximization (1)

feature-extraction (1)

filtering (1)

forecasting (1)

gaussian-processes (1)

generative-models (1)

ggplot (1)

gibbs-sampling (1)

gradient-descent (1)

hidden-markov-models (1)

hyperparameter-optimization (1)

image-processing (1)

interactive (1)

ios (2)

ipad (2)

jax (1)

JAX (1)

keras (2)

kernel-methods (1)

keyboard-shortcuts (1)

LA (1)

linear-algebra (1)

linear-regression (2)

machine learning (1)

macos (2)

marimo (1)

markdown (1)

matrix-decomposition (1)

mcmc (2)

mixture-models (1)

ML (87)

ml (2)

mobile-development (1)

monte-carlo (1)

multi-label classification (1)

natural language processing (1)

networking (1)

neural-architecture-search (1)

neural-networks (5)

news (1)

nlp (2)

object-detection (1)

optimization (2)

pandas (1)

parameter-estimation (1)

plotnine (1)

probabilistic-models (7)

productivity (5)

python (4)

pytorch (5)

PyTorch (3)

recommendation-systems (1)

remote-development (1)

sampling-methods (1)

scipy (1)

sequence modeling (1)

sequence-alignment (1)

sequence-modeling (2)

sequence-to-sequence (1)

setup (6)

shortcuts (2)

signal-processing (2)

simulation (1)

sleep (1)

softmax (1)

ssh (1)

statistics (1)

sustainability (1)

temperature scaling (1)

tensorflow (2)

terminal (1)

text generation (1)

TF (3)

TFP (3)

time-series (4)

tools (2)

transformers (3)

uncertainty-quantification (2)

unsupervised-learning (1)

variational-inference (1)

visualisation (3)

visualization (3)

vscode (1)

workflow (1)

yolo (1)

Temperature Scaling in Softmax: Controlling Randomness in Language Models

deep learning

natural language processing

softmax

temperature scaling

text generation

Exploring how temperature scaling affects the randomness and diversity of language model outputs through mathematical analysis and interactive visualizations

Multi-Image Classification with VOC Dataset Visualization

computer vision

deep learning

multi-label classification

data visualization

Visualizing and filtering multi-image classification samples from the VOC dataset for improved training data quality

Logit Masking for Sleep Stage Classification

machine learning

deep learning

sleep

sequence modeling

Demonstrating how logit masking enforces valid transitions in sleep stage classification

Slack Tips for Better Team Management

productivity

tools

Here are some useful Slack tips to improve your team communication and channel management.

Interactive Data Science with Marimo

python

interactive

data-science

marimo

Exploring Marimo’s reactive notebook capabilities integrated with Quarto

Keyboard shortcuts on Mac

setup

macos

shortcuts

productivity

keyboard-shortcuts

workflow

Keyboard shortcuts on mac

Time Series Forecasting - Comparing MLP and Transformer Models

ML

time-series

forecasting

deep-learning

transformers

pytorch

import numpy as np
import matplotlib.pyplot as plt
%matplotlib inline
%config InlineBackend.figure_format = 'retina'
import torch
import torch.nn as nn
import torch.nn.funct…

Character-Level Attention Mechanism for Name Generation

ML

—author: Nipun Batrabadges: truecategories:- MLdate: ’2024-05-30’title: Character-Level Attention Mechanism for Name Generationtoc: true—

Object detection

ML

computer-vision

object-detection

deep-learning

neural-networks

yolo

pytorch

—author: Nipun Batrabadges: truecategories:- ML- computer-vision- object-detection- deep-learning- neural-networks- yolo- pytorchdate: ’2024-05-30’title: Object…

Attention in Sequence to Sequence

ML

attention-mechanism

sequence-to-sequence

deep-learning

neural-networks

transformers

nlp

pytorch

—author: Nipun Batrabadges: truecategories:- ML- attention-mechanism- sequence-to-sequence- deep-learning- neural-networks- transformers- nlp- pytorchdate…

Character-Level RNN for Name Generation

ML

—author: Nipun Batrabadges: truecategories:- MLdate: ’2024-05-30’title: Character-Level RNN for Name Generationtoc: true—

Sampling Distribution Analysis - Mean vs Standard Deviation

ML

—author: Nipun Batrabadges: truecategories:- MLdate: ’2024-05-07’title: Sampling Distribution Analysis - Mean vs Standard Deviationtoc: true—

Mixture of Experts

ML

import numpy as np
import matplotlib.pyplot as plt
%matplotlib inline
%config InlineBackend.figure_format = 'retina'
import torch
import torch.nn as nn
import torch.nn.funct…

Logo

ML

import numpy as np
import matplotlib.pyplot as plt
%matplotlib inline
%config InlineBackend.figure_format = 'retina'

Basic Neural Process

ML

import numpy as np
import matplotlib.pyplot as plt
%matplotlib inline
import torch
import torch.nn as nn
import torch.nn.functional as F
%config InlineBackend.figure_format =…

Using a neural network as a covariance function

ML

import torch
import torch.nn as nn
import matplotlib.pyplot as plt
import numpy as np
# Retina mode
%config InlineBackend.figure_format = 'retina'

# Create training and…

Towards Transformers

ML

transformers

attention-mechanism

deep-learning

neural-networks

nlp

sequence-modeling

pytorch

—author: Nipun Batrabadges: truecategories:- ML- transformers- attention-mechanism- deep-learning- neural-networks- nlp- sequence-modeling- pytorchdate: ’2023-12-21’title…

Naive implementation of Strassen’s algorithm

ML

import numpy as np 
import time
import matplotlib.pyplot as plt
import pandas as pd
# Retina display
%config InlineBackend.figure_format = 'retina'

log_size = 8
size = 2…

YouTube video to transcript using openAI whisper and summary using OLLama

ML

Reinforcement Learning

ML

Super Resolution using U-Net like architecture

ML

import matplotlib.pyplot as plt
import torch

%matplotlib inline
%config InlineBackend.figure_format='retina'

# Download some MNIST to demonstrate super-resolution
from …

Trees using NetworkX

ML

import networkx as nx
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd

%matplotlib inline

# Retina display
%config InlineBackend.figure_format = 'ret…

Positional Encoding

ML

import numpy as np
import matplotlib.pyplot as plt
import torch
import seaborn as sns
import pandas as pd

dist =torch.distributions

sns.reset_defaults()
sns.set_context(…

Bayesian Active Learning with Disagreement (BALD)

ML

import numpy as np
import matplotlib.pyplot as plt
import torch
import seaborn as sns
import pandas as pd

dist =torch.distributions

sns.reset_defaults()
sns.set_context(…

Gradient wrt input for a simple model for adversarial attacks

ML

PINN

ML

PINNs are a class of neural networks for solving partial differential equations. They are trained to minimize the residual of the differential equation, and the boundary and…

SIREN paper implementation

ML

Reconstruction from ReLU

Reconstruction from Sine

SIREN paper

ML

In this post, I’m noting some observations from the SIREN paper.

Heteroskedastic and Homoskedastic MLPs in PyTorch for regression

ML

Tensorboard

ML

import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim

import numpy as np
import matplotlib.pyplot as plt

from torch.utils.data imp…

Residual Connections in PyTorch

ML

import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim

import numpy as np
import matplotlib.pyplot as plt

from torch.utils.data imp…

AutoML PyTorch

ML

automl

neural-architecture-search

hyperparameter-optimization

automated-machine-learning

pytorch

—author: Nipun Batrabadges: truecategories:- ML- automl- neural-architecture-search- hyperparameter-optimization- automated-machine-learning- pytorchdate…

Stacking (Meta Learning)

ML

Stacking (Ensemble Learning)

ML

In this post, we study a simple meta learning technique called Stacking

Multivariate Taylor Series

ML

Second order Taylor series expansion of a function f around a point (x0, y0) is given by (when using the vector notation)

Comparing GP libraries

ML

In this notebook, we will show how to compare different GP libraries to give the same loss for a simple GP regression problem.

Understanding Singular Value Decomposition with Visualizations

ML

linear-algebra

matrix-decomposition

dimensionality-reduction

visualization

jax

—author: Nipun Batrabadges: truecategories:- ML- linear-algebra- matrix-decomposition- dimensionality-reduction- visualization- jaxdate: ’2023-02-01’output-file…

Conformal Prediction

ML

This is a work in progress. I will be adding more content to this post in the coming days.

VSCode Settings and Tips

ML

vscode

Shortcut	Action
Cmd + Shift + P	Open command palette
Ctrl + `	Toggle terminal
Cmd + B	Toggle sidebar
Cmd + Ctrl + F	Toggle full screen

Binomial and Poisson distribution

ML

import jax.numpy as jnp
import jax
from jax import random
import tensorflow_probability.substrates.jax as tfp
tfd = tfp.distributions
import pandas as pd

import matplotlib.…

Some useful tidibts in sympy

ML

Some useful tidibts in sympy

Autoencoders in JAX

ML

A programming introduction to Autoencoders in JAX

Calibration

ml

Probability Calibration

Multi-output Gaussian Process

ml

Multi-output Gaussian Process

Welcome To My Blog

news

This is the first post in a Quarto blog. Welcome!

Tristan O’Malley

Audio Filtering

ML

import numpy as np
import matplotlib.pyplot as plt
import torch
import seaborn as sns
from functools import partial

sns.reset_defaults()
sns.set_context(context="talk"…

Coordinate descent failure example

ML

Pyro Conditioning

ML

import numpy as np
import matplotlib.pyplot as plt
import torch
import seaborn as sns
import pandas as pd
import pyro

dist =pyro.distributions

sns.reset_defaults()
sns.s…

Linear Regression using Pyro

ML

import numpy as np
import matplotlib.pyplot as plt
import torch
import seaborn as sns
import pandas as pd

t_dist =torch.distributions

sns.reset_defaults()
sns.set_contex…

Probabilstic PCA using PyTorch distributions

ML

import numpy as np
import matplotlib.pyplot as plt
import torch
import seaborn as sns
import pandas as pd

dist =torch.distributions

sns.reset_defaults()
sns.set_context(…

Drawing graphical models

ML

GMM

ML

mixture-models

clustering

expectation-maximization

probabilistic-models

unsupervised-learning

—author: Nipun Batrabadges: truecategories:- ML- mixture-models- clustering- expectation-maximization- probabilistic-models- unsupervised-learningdate…

Logistic Regression using PyTorch distributions

ML

import numpy as np
import matplotlib.pyplot as plt
import torch
import seaborn as sns
import pandas as pd

dist =torch.distributions

sns.reset_defaults()
sns.set_context(…

Variational inference

ML

variational-inference

bayesian

approximate-inference

probabilistic-models

optimization

—author: Nipun Batrabadges: truecategories:- ML- variational-inference- bayesian- approximate-inference- probabilistic-models- optimizationdate: ’2022-02-12’output-file…

Maximum A-Posteriori (MAP) for parameters of univariate and multivariate normal distribution in PyTorch

ML

PyTorch

\(\hat{\theta}_{MAP}=\dfrac{n}{n+\sigma^{2}} \bar{x}+\dfrac{\sigma^{2}}{n+\sigma^{2}} \mu\)

Matrix as transformation and interpreting low rank matrix

ML

LA

Multiplying a matrix A with a vector x transforms x

Maximum Likelihood Estimation (MLE) for parameters of univariate and multivariate normal distribution in PyTorch

ML

PyTorch

Let us generate some normally distributed data and see if we can learn the mean.

Autograd in JAX and PyTorch

ML

JAX

PyTorch

import torch
from jax import grad
import jax.numpy as jnp

Coin Toss (MLE, MAP, Fully Bayesian) in TF Probability

ML

TFP

TF

We will be studying the problem of coin tosses. I will not go into derivations but mostly deal with automatic gradient computation in TF Probability.

Linear Regression in TF Probability using JointDistributionCoroutineAutoBatched

ML

TFP

TF

Simple Directed Graphical Models in TF Probability

ML

TFP

TF

Sampling from univariate and multivariate normal distributions using Box-Muller transform

ML

In this notebook I’ll talk about sampling from univariate and multivariate normal distributions. I’ll mostly directly write the code and show the output. The excellent…

Understanding KL-Divergence

ML

Let us first look at G1. Look at the illustration below. We have a normal distribution \(p\) and two other normal distributions \(q_1\) and \(q_2\). Which of \(q_1\) and \(q_…

Linear Regression in Tensorflow Probability

ML

Good reference https://tensorchiefs.github.io/bbs/files/21052019-bbs-Beate-uncertainty.pdf

Testing out some distributions in Tensorflow Probability

ML

Let us generate some normally distributed data and see if we can learn the mean.

Learning Gaussian Process regression parameters using mini-batch stochastic gradient descent

ML

How to learn the parameters of a GP

Linear Regression from scratch in Julia

ML

using Plots
theme(:default)

using LinearAlgebra
using LaTeXStrings

Probabilistic Programming in Pyro

ML

In this post, I will look at a simple application:

Blurring an image selectively using Affinity Photo

setup

Blurring an image selectively using Affinity Photo

Audio filters

signal-processing

audio

filtering

digital-signal-processing

python

scipy

Audio filtering techniques and applications

Running Python scripts on server over ssh and getting back content

setup

python

ssh

remote-development

networking

terminal

Running Python scripts on server over ssh and getting back content

Some of my shortcuts on the iPad

setup

ipad

shortcuts

automation

productivity

ios

Some of my shortcuts on the iPad

My iPad Setup

setup

ipad

mobile-development

productivity

ios

My iPad computing setup

My Mac Setup

setup

macos

development-environment

productivity

tools

My Mac Setup

GAN

ML

deep-learning

generative-models

adversarial-networks

neural-networks

keras

tensorflow

Implementation and visualization of Generative Adversarial Networks

Understanding Kernels in Gaussian Processes Regression

ML

Using GPy and some interactive visualisations for understanding GPR and applying on a real world data set

Sampling from common distributions

ML

From the ground up!

Learning Gaussian Process regression parameters using gradient descent

ML

How to learn the parameters of a GP

Active Learning with Bayesian Linear Regression

ML

A programming introduction to Active Learning with Bayesian Linear Regression.

Zeel Patel & Nipun Batra

Some experiments in Gaussian Processes Regression

ML

Using GPy and some interactive visualisations for understanding GPR and applying on a real world data set

Some Neural Network Classification

ML

A programming introduction to NNs.

Neural Networks from scratch

ML

Simple scripts for downloading weather data

Learning neural network for XOR

ML

Excellent, now let us start from random weight initialisations and use backprop to come to our result

Bayesian Linear Regression

ML

bayesian

linear-regression

uncertainty-quantification

probabilistic-models

statistics

A programming introduction to Bayesian Linear Regression.

An Example Markdown Post

markdown

A minimal example of using markdown with fastpages.

Gaussian Processes

ML

gaussian-processes

bayesian

uncertainty-quantification

probabilistic-models

kernel-methods

An interactive exploration of Gaussian processes.

Placement-Preparation-2018-1-HashMap

academia

HashMaps for programming interviews

Visualising Electricity Access Over Space and Time

sustainability

How is the world changing over the years!

Mapping location of air quality sensing in India

air quality

AQ sensing in India

Active Learning

ML

A programming introduction to query by committee strategy for active learning

Signal denoising using RNNs in PyTorch

ML

Denoising

CS Ph.D. lessons to my younger self

academia

Some personal reflections..

Neural Networks for Collaborative Filtering

ML

Neural networks to learn the embeddings! and how to combine them

Recommend keras

ML

recommendation-systems

collaborative-filtering

deep-learning

neural-networks

keras

tensorflow

—author: Nipun Batrabadges: truecategories:- ML- recommendation-systems- collaborative-filtering- deep-learning- neural-networks- keras- tensorflowdate…

Adagrad based matrix factorization

ML

Adagrad optimizer for matrix factorisation

Linear regression adagrad vs gd

ML

optimization

gradient-descent

adagrad

linear-regression

algorithms

—author: Nipun Batrabadges: truecategories:- ML- optimization- gradient-descent- adagrad- linear-regression- algorithmsdate: ’2017-08-12’output-file…

Fifty ggplot python 1

visualization

data-visualization

ggplot

plotnine

python

data-analysis

—author: Nipun Batrabadges: truecategories:- visualization- data-visualization- ggplot- plotnine- python- data-analysisdate: ’2017-08-02’output-file…

Linear regression with prior (using gradient descent)

ML

What if we start from some prior!

Data exploration using widgets in Matplotlib

visualisation

Exploring data in Matplotlib

Constrained Non-negative matrix factorisation using CVXPY

ML

Constrained NMF using CVXPY!

Out of Tensor factorisation

ML

Out of tensor factorisation

Out of matrix non-negative matrix factorisation

ML

What if we to predict for entries not within the matrix?!

MCMC coins

ML

bayesian

mcmc

monte-carlo

probabilistic-models

parameter-estimation

—author: Nipun Batrabadges: truecategories:- ML- bayesian- mcmc- monte-carlo- probabilistic-models- parameter-estimationdate: ’2014-07-01’output-file…

Latexify Matplotlib

visualisation

Towards amazing plots in research papers!

Programatically understanding Expectation Maximization

ML

Maximize based on what you know, re-estimate!

DTW

ML

time-series

dynamic-time-warping

sequence-alignment

algorithms

distance-metrics

—author: Nipun Batrabadges: truecategories:- ML- time-series- dynamic-time-warping- sequence-alignment- algorithms- distance-metricsdate: ’2014-05-01’output-file…

Gibbs sampling

ML

bayesian

mcmc

gibbs-sampling

probabilistic-models

sampling-methods

—author: Nipun Batrabadges: truecategories:- ML- bayesian- mcmc- gibbs-sampling- probabilistic-models- sampling-methodsdate: ’2014-05-01’output-file…

Denoising

ML

signal-processing

denoising

image-processing

feature-extraction

—author: Nipun Batrabadges: truecategories:- ML- signal-processing- denoising- image-processing- feature-extractiondate: ’2013-09-01’output-file…

HMM Simulation for Continuous HMM

ML

Simulating a continuous HMM

HMM simulate

ML

hidden-markov-models

sequence-modeling

probabilistic-models

time-series

simulation

—author: Nipun Batrabadges: truecategories:- ML- hidden-markov-models- sequence-modeling- probabilistic-models- time-series- simulationdate: ’2013-06-01’output-file…

Aggregation timeseries

time-series

data-aggregation

data-analysis

pandas

visualization

—author: Nipun Batrabadges: truecategories:- time-series- data-aggregation- data-analysis- pandas- visualizationdate: ’2013-05-01’output-file…

Downloading weather data

visualisation

Simple scripts for downloading weather data