admin

Strimlit Library

Streamlit

If you are a data scientist who doesn’t want to spend time on creating a website, and you still wish to show the results of your work, this is perfect for you: Check it out. I’m alrady using it 🙂 ... Read More
Facebook Chatbot

Tonight Talk with Facebook Chatbot

Facebook recently opensourced its Blender chatbot: I downloaded it, started it and had a short talk with it, as follows: Enter Your Message: hi there. how are you?[TransformerGenerator]: i ‘ m doing well . how about you ? what do you like to do in your spare time ?Enter Your ... Read More
Minority Report

Remember Minority Report?

Do you remember Minority Report movie? Well, it is not that far away from now. But anyway, in USA they don’t make it on the right way … ... Read More

Is PyTorch More Attractive Than TensorFlow?

PyThorch 1.5 is good. Also TensorFlow 2.x. But, did Google made several bad decisions with the initial design of Tensorflow, starting with beta and 1.x versions? Check the number of the downloads of each of the Deep NLP models available on ... Read More
AI news

What Happened Last Several Days in AI?

Hi I missed posting something about AI because I was swamped. In this post, I’ll share with you some of the new and exciting things that I noticed in the last several days. ACME First reinforcement learning framework I’ve ever heard, probably just arrived: And another thing from DeepMind open-sourced: ... Read More
GPT-3

GPT-3 … OMG

OpenIA released GPT-3. For the NLP enthusiasts it is not necessary to explain why does this matter 🙂 Anyway, few links on the toppic: Top editor’s note: Now it doesn’t need fine-tuning per specific task. They created a new milestone in NLP and AI in general. ... Read More
Pose Animator with TensorFlow for JS

Body Movements with TensorFlow

Want to see TensorFlow performing in realtime in the browser?See how it mimics your body movements with your image captured with webcam, in the browser. TensorFlow model up and running, with JS … ... Read More
Deploying Machine Learnng Models

Deploying Machine Learning Models

Introduction Deploying machine learning models into production is a separate step of the Machine Learning pipeline. It comes after the research phase, covered with analyzing data, feature engineering, and feature selection. The Machine Learning model shows its full value when the company that produced it is generating predictions using fully ... Read More
Feature Selection for Machine Learning

Feature Selection in Machine Learning

Feature Selection Introduction Feature selection is a method of selecting a subset of all features provided with observations data to build the optimal Machine Learning model. Well implemented feature selection leads to faster training and inference as well as better performing trained models. Other benefits from proper feature selection are ... Read More