About
Articles by Nikunj
-
Exploring the Evolution Beyond Transformers: Unveiling the Power of State Space Models with Mamba
Exploring the Evolution Beyond Transformers: Unveiling the Power of State Space Models with Mamba
By Nikunj Kotecha
-
Quick Guide to Quantization in Machine Learning
Quick Guide to Quantization in Machine Learning
By Nikunj Kotecha
-
Top 20 Linux Commands for every Machine Learning Engineer
Top 20 Linux Commands for every Machine Learning Engineer
By Nikunj Kotecha
Contributions
Activity
-
I always thought Mac is great and that it's been wonderful for development and professional use. However, I felt there was something missing that…
I always thought Mac is great and that it's been wonderful for development and professional use. However, I felt there was something missing that…
Shared by Nikunj Kotecha
-
🎬 Incredible Video! Check out the latest release from Studio Tim Fu where they used OpenAI Sora text to video model to generate a truly immersive…
🎬 Incredible Video! Check out the latest release from Studio Tim Fu where they used OpenAI Sora text to video model to generate a truly immersive…
Shared by Nikunj Kotecha
-
Edge Impulse donates 1% of our revenue to organizations that help protect our world. Earlier this year we started working with WildTrack.org, who…
Edge Impulse donates 1% of our revenue to organizations that help protect our world. Earlier this year we started working with WildTrack.org, who…
Liked by Nikunj Kotecha
Experience & Education
Licenses & Certifications
Volunteer Experience
Publications
-
Dynamic cross-feature fusion for american sign language translation
2021 16th IEEE International Conference on Automatic Face and Gesture Recognition
-
Deep learning methods for sign language translation
ACM Transactions on Accessible Computing (TACCESS)
-
Adding uncertainty to Dermatological Assistance
SPIE medical imaging conference
- Introduced uncertainty to the deep neural network by adding variational inference in the penultimate layer
- Reduced false negative by combined Machine learned features and traditional hard-thresholding approachesOther authorsSee publication
Courses
-
Advanced Computer Vision
-
-
Big Data Analytics
-
-
Deep Learning
-
-
Foundation of Algorithms
-
-
Foundation of Computer Vision
-
-
Hardware IP design, Neurmorphic Computing and BrainChip Akida
-
-
Independent Study - Analysis on user behavior with mental health chatbot
-
-
Introduction to Big Data
-
-
Introduction to MetaTF - Akida Machine Learning Framework
-
-
Introduction to Neuromorphic AI
-
-
Machine Intelligence
-
-
Pattern Recognition
-
Projects
-
Faster Objects More Objects Detection with Neurmorphic AI
-
-
Preventive Maintainance using Neuromorphic Accelerator
-
-
Drone Voice Keyword on Neuromorphic Accelerator
-
-
Analysis on user behavior with mental health chatbot
-
- Developed a LSTM autoencoder model to predict if the user will enter in a state of crisis using Python and Keras
- Explored patterns in user messages with Kmeans and DBSCAN clustering analysis using Python and Scikit-learn
- Generated Wordclouds to identify most frequent words used before and after the state of crisis -
Interpreting Handwritten math expression
-
- Improved accuracy by 2% with RandomForest classifier for identifying and parsing a handwritten math expression
- Collected the data into a SQL database and performed data cleaning and feature engineering for given expressions
- Implemented classification, segmentation and parsing for handwritten math expressionsOther creators -
Breast Cancer classification on Histopathology images
-
- Implemented a depthwise separable CNN neural network to predict breast cancer using Keras
- Generated classification reports such as accuracy, F1 score, specificity, and sensitivity -
Image segmentation of melons in Computer Vision
-
This project focuses on Segmenting an image consisting of multiple watermelons in it.
It follows the approach of Supervised Learning.
In order to create a model, first provide an image where multiple cut pieces of watermelons are present. Then give few inputs for the skin and foreground of the melons.
The program uses the concept of Mahalanobis distance and segments the melons with respect to skin and foreground and draws a blue line separating the two.
You can use the model…This project focuses on Segmenting an image consisting of multiple watermelons in it.
It follows the approach of Supervised Learning.
In order to create a model, first provide an image where multiple cut pieces of watermelons are present. Then give few inputs for the skin and foreground of the melons.
The program uses the concept of Mahalanobis distance and segments the melons with respect to skin and foreground and draws a blue line separating the two.
You can use the model generated and pass on any image having melons pieces and the program will use this model and provide a segmented output. -
Motion of diver in one frame
-
- Developed an algorithm that shows all the positions of a diver in one frame using Background subtraction and OpenCV
- Implemented a background model that could separate the diver and the background in the video -
Recognition of Hindi Language characters
-
- Developed a CNN based neural network using Tensorflow that recognizes characters in Hindi language
- Visualized, preprocessed and analyzed the given data for Hindi language characters -
Social media sentiment analysis
-
This project is implemented solely for learning purposes.
The code and project direction is influenced by https://medium.com/@martinpella/customers-tweets-classification-41cdca4e2de
The dataset used for this project is called "Airline sentiment tweets" and can be found here: https://www.kaggle.com/tango911/airline-sentiment-tweets
In this project, first pre-processing steps are taken place. In this text cleaning and any unwanted noise is removed.
The data are split into…This project is implemented solely for learning purposes.
The code and project direction is influenced by https://medium.com/@martinpella/customers-tweets-classification-41cdca4e2de
The dataset used for this project is called "Airline sentiment tweets" and can be found here: https://www.kaggle.com/tango911/airline-sentiment-tweets
In this project, first pre-processing steps are taken place. In this text cleaning and any unwanted noise is removed.
The data are split into training and test set for better learning of the model.
Text vectorization is implemented after this using the Tf-IFD method and sparse vectors are generated.
Logistic regression is used to train the model.
The model is able to achieve an average of 80% accuracy. It is able to classify tweets into neutral, negative and positive sentiments with this accuracy.
More activity by Nikunj
-
Announcing new visual evaluation comparisons in W&B Weave. Easily compare model performance, latency, and token usage in a comprehensive view. Watch…
Announcing new visual evaluation comparisons in W&B Weave. Easily compare model performance, latency, and token usage in a comprehensive view. Watch…
Liked by Nikunj Kotecha
-
New blog post from BrainChip: "Enter TENNs: A New Paradigm in Audio Processing." This post details our TENNs-powered Audio Denoising solution, which…
New blog post from BrainChip: "Enter TENNs: A New Paradigm in Audio Processing." This post details our TENNs-powered Audio Denoising solution, which…
Liked by Nikunj Kotecha
-
My wife and I recently did a 12 day trip to Banff Canada for a total cost of $1103.15. That’s less than $100/day. How did we do it for so cheap? We…
My wife and I recently did a 12 day trip to Banff Canada for a total cost of $1103.15. That’s less than $100/day. How did we do it for so cheap? We���
Liked by Nikunj Kotecha
-
Apart from generative AI, these three technologies offer exciting opportunities for startups. Neuromorphic engineering, led by BrainChip Holdings'…
Apart from generative AI, these three technologies offer exciting opportunities for startups. Neuromorphic engineering, led by BrainChip Holdings'…
Liked by Nikunj Kotecha
Other similar profiles
Explore collaborative articles
We’re unlocking community knowledge in a new way. Experts add insights directly into each article, started with the help of AI.
Explore MoreOthers named Nikunj Kotecha
-
Nikunj Kotecha
-
Nikunj Kotecha
Remote Support Engineer at Ministry of Justice UK
-
Nikunj Kotecha
Student at Institute Of Chartered Accountancy Of India - CA finalist Article Assistant at Jayantilal Thakkar and Co.
-
Nikunj Kotecha
Maa canvassig brokar at Mugfli arenda
7 others named Nikunj Kotecha are on LinkedIn
See others named Nikunj Kotecha