Welcome
Pranay singh
Machine Learning Engineer
ABOUT ME
Machine Learning Engineer
I'm a Machine Learning Engineer. My interest lies in the depth of Machine Learning Algorithms, fundamental mathematics, and areas of Deep Learning. I am working on various things in the field of Computer Vision. My current projects deal with Image and Video Processing frameworks that work with surveillance and Recognition cameras. Skills that I am building currently are Object and Feature Detection, Segmentation and Classification. I love to follow the ongoing advancements and research in AI.
​
I also love to travel, listen to music, and make acquaintances.
What Made me get into ML
My journey into Machine Learning began during my undergraduate studies, where I was captivated by the potential of algorithms to solve real-world problems. This passion led me to specialize in Computer Vision, focusing on Image and Video Processing frameworks for surveillance and recognition systems
SKILLS
My Machine learning competencies include:
-
Machine Learning Algorithms: Classification, Regression, KNN, SVM, Decision Trees​
-
Programming Languages: Python​
-
Building efficient Machine Learning Pipeline
-
Supervised Learning: Classification and Regression, KNN, Support Vector Machines, Decision Trees.
-
Ensemble Learning: Random Forests, Bagging and Pasting
-
Boosting Algorithms- AdaBoosting, Gradient Boosting
-
Deep Learning: CNN, RNN, LSTM, Transfer Learning​
-
Computer Vision: Image & Video Processing, Image Segmentation and Localization, Object detection, Feature Extraction, HOG, ORB, YOLO, RCNN, Detectron.
-
Libraries: PyTorch, TensorFlow, Keras, Scikit-learn, Pandas, NumPy, Matplotlib, Seaborn
​
PROJECTS
My Projects revolve around applications of Deep Learning and Computer Vision that try to solve some of the interesting problems we have, along with those of advanced Machine Learning algorithms that generate interesting insights from the data, and produce reliable inferences.
Automatic Image Captioning
Image of the Model Architecture
Description: Generate Descriptive Captions For An Image. A CNN-RNN neural network architecture to automatically generate captions from images describing that image. The network consists of a pre-trained ResNet50 CNN encoder connected to an RNN decoder.
​Technologies Used: Python, TensorFlow, Keras, ResNet50, RNN
FACIAL KEYPOINTS DETECTION
Representation of Facial Keypoints used by the model to train
Description: Identify Distinguishing Keypoints On a face
A Facial Keypoints Detection model using a CNN that takes in any image with faces, predicts the location of 68 distinguishing Keypoints on each face, and marks them at their correct position on the face.
​
Technologies Used: Python, PyTorch, OpenCV
CREDIT CARD FRAUD DETECTION
High Precision Model
Description: Predicting Fraudulence on Highly Unbalanced Data
Built a Classifier to detect Fraud Credit Card Transactions trained over a dataset listing 284,807 transaction details of anonymous European cardholders. A Random Forest classifier achieved 90% Precision, 70% Recall, and 85% AUC score.
​
​Technologies Used: Technologies Used: Python, Scikit-Learn
CORPORATE WORK EXPERIENCE
​Machine Learning Engineer - Spectral Tech Private Limited(KMG)
​​
-
Led research and development of Surveillance Software based on Video Processing with Object Detection.
-
Significantly optimized solutions to decrease the False Detection rate and bring down the boot time and
processing speed of algorithms. -
Developed solutions for new problems such as identification of a person under a face mask.
​
TECHNOLOGIES WORKED ON: PYTHON, TENSORFLOW, JIRA
November 2020 - Present
​Research & Development Engineer - Ampviv Healthcare Private Limited
​​
-
Responsible for analysis, implementation, development, performing preliminary testing and deployment of the product being developed by the company along with writing, editing and maintaining papers and reports of the work undertaken.
-
Led the complete development of the Machine Learning framework used by the product and partly of the Image Processing work along with other team members under the guidance of the mentor.
-
Led the iOS application development for deployment of our product.
-
Research, study and implementation of various research papers and articles, engage with other developers in open-source communities and forums in order find solutions, curate ideas and problem solving related to the development of our product.
​
TECHNOLOGIES WORKED ON: PYTHON, TENSORFLOW, JIRA
September 2020 - September 2021
COURSES
COMPUTER VISION
Udacity
Learn about Gradient Descent Algorithm, the idea behind it, break down the equation and implement the algorithm from scratch on Boston Housing dataset.
LET'S CONNECT!
Feel free to hit me up for any discussions, collaborations, recruitment, or feedback!
​
+1 4375571359
