satishjasthi Goto Github PK

followers: 28.0 following: 51.0 repos: 339.0 gists: 9.0

Name: SATISH J

Type: User

Company: Detalytics

Bio: Machine learning Fanatic

Location: India

Blog: https://twitter.com/SatishJasthiJ

Projects

Predicting Stock prices using Deep learning (Apr 2017 - Apr 2017)

Description: Evaluated the performance of LSTM network to predict Google close stock price. Addressed the issue of vanishing gradient in long-term sequences using long short term memory architecture, and developed a model to predict the stock price, approximates the actual value.
See project here

Train a Smartcab to Drive (Mar 2017 - Mar 2017)

Description: Applied reinforcement learning to build a simulated vehicle navigation agent. This project involved modelling a complex control problem in terms of limited available inputs, and designing a scheme to automatically learn an optimal driving strategy based on rewards and penalties.
See project here

Creating Customer Segments (Feb 2017 - Feb 2017)

Description: Reviewed unstructured data to understand the patterns and natural categories that the data fits into. Used multiple algorithms and both empirically and theoretically compared and contrasted their results. Made predictions about the natural categories of multiple types in a dataset, then checked these predictions against the result of unsupervised analysis.
See project here

Finding Donors for CharityML (Feb 2017 - Feb 2017)

Description: Investigated factors that affect the likelihood of charity donations being made based on real census data. Developed a naive classifier to compare testing results to. Trained and tested several supervised machine learning models on preprocessed census data to predict the likelihood of donations. Selected the best model based on accuracy, a modified F-scoring metric, and algorithm efficiency.
See project here

SATISH J's Projects

python-guide

Python best practices guidebook, written for Humans.

pytorch

Tensors and Dynamic neural networks in Python with strong GPU acceleration

pytorch-lightning

The lightweight PyTorch wrapper for high-performance AI research. Scale your models, not the boilerplate.

MobileNetV1, MobileNetV2, VGG based SSD/SSD-lite implementation in Pytorch 1.0 / Pytorch 0.4. Out-of-box support for retraining on Open Images dataset. ONNX and Caffe2 support. Experiment Ideas like CoordConv.

pytorch-tree-lstm

Pytorch implementation of the child-sum Tree-LSTM model

pytorch-yolov3

Minimal PyTorch implementation of YOLOv3

pytorch_cifar10

Pretrained TorchVision models on CIFAR10 dataset (with weights)

pytudes

Python programs, usually short, of considerable difficulty, to perfect particular skills.

randomforest-for-novice

Article on Random forest

rapids-lab

Data Science workshop with RAPIDS

recipes

reinforcement-learning

Implementation of Reinforcement Learning Algorithms. Python, OpenAI Gym, Tensorflow. Exercises and Solutions to accompany Sutton's Book and David Silver's course.

render

A simple rendering engine and application written in Java.

resnext

Implementation of a classification framework from the paper Aggregated Residual Transformations for Deep Neural Networks

resources-for-learning-hacking

All the resources I could find for learning Ethical Hacking and penetration testing.

review_object_detection_metrics

Object Detection Metrics. 14 object detection metrics: mean Average Precision (mAP), Average Recall (AR), Spatio-Temporal Tube Average Precision (STT-AP). This project supports different bounding box formats as in COCO, PASCAL, Imagenet, etc.