Name: Archishman Satpathy
Type: User
Company: IIIT BHUBANESWAR
Bio: Data Scientist, Content Writer, Sales Executive, Former CEO of TEM,
Team Partner and Contributor - ARPITA GHADAI
@IIIT BHUBANESWAR
Twitter: theenthusiast28
Location: Bhubaneswar, Odisha, India
Blog: https://medium.com/@archish2002
Archishman Satpathy's Projects
I have designed this cervical cancer detection model ResNet-50 which has 48 Convolution layers along with 1 MaxPool and 1 Average Pool layer. While the original Resnet had 34 layers and used 2-layer blocks, other advanced variants such as the Resnet50 made the use of 3-layer bottleneck blocks to ensure improved accuracy and lesser training time.
This is my college mega project assigned to me and my teammate - Aayush Choudhary on our final semester of B.Tech. The project title was "COVID 19 TIME SERIES FORECASTING USING XGBOOST AND ARIMA MODEL (HYBRID)". There is also a research paper prepared for this project.
This repository holds the code for a ML model on "Events Recommender Service" where the model takes various parameters, proficiencies and levels as input and then extracts recommendations of events for learning of an user based on those inputs.
Use Gemini and ChatGPT to learn from two capable teachers Use Google's latest model release, Gemini, to teach you what you want to know and compare those with ChatGPT's responses. The models are specifically prompted not to generate extra text to make it easier to compare any differences.
Here are all my solutions for the GFG POTD.
A collection of C++ codes for Geeks for Geeks Problem of the Day
This is my first Generative AI model trained with 1000 epochs and batch size 64.
My first python turtle graphics using Py3.
GFG potd solutions
This repository holds the code for a ML model on "Programs Recommender Service" where the model takes various parameters, proficiencies and levels as input and then extracts recommendations of programs…
Training of neural networks for automated diagnosis of pigmented skin lesions is hampered by the small size and lack of diversity of available dataset of dermatoscopic images. I tackle this problem by releasing the HAM10000 ("Human Against Machine with 10000 training images") dataset. The final dataset consists of 10015 dermatoscopic images.