Jan Belke (@janbelke) header
Jan Belke (@janbelke) profile picture

Worked for 10+ years in tech and now starting my own ventures. Looking forward to connect.

San Francisco
Joined June 2010
Photo by Jan Belke (@janbelke)Photo by Jan Belke (@janbelke)Photo by Jan Belke (@janbelke)Photo by Jan Belke (@janbelke)Photo by Jan Belke (@janbelke)Photo by Jan Belke (@janbelke)Photo by Jan Belke (@janbelke)Photo by Jan Belke (@janbelke)
“Love the life you live. Live the life you love.” – Bob Marley
3
Terrific!
#NASAWebb is fully deployed! 🎉 With the successful deployment & latching of our last mirror wing, that's: 50 major deployments, complete. 178 pins, released. 20+ years of work, realized. Next to #UnfoldTheUniverse: traveling out to our orbital destination of Lagrange point 2!
Autoencoders are a specific type of feedforward neural network where the input is the same as the output. They compress the input into a lower-dimensional code and then reconstruct the output from this representation. Follow @DrivenScience #MachineLearning #NeuralNetworks
1
4
1
5
Jobs that robots will replace in the future: 👉🏻 Customer service executives 👉🏻 Bookkeeping and data entry 👉🏻 Receptionists 👉🏻 Manufacturing 👉🏻 Retail and Courier 👉🏻 Taxi and bus drivers 👉🏻 Market research analysts 👉🏻 Security guards 👉🏻 Follow @DrivenScience #MachineLearning
4
3
Competitive Data Science Platforms Other Than Kaggle: - Driven Data - CrowdANALYTIX - Innocentive - TunedIT - Codalab - ZINDI - DATASOURCE. AI - Alibaba Cloud Tianchi - Bitgrit - Analytics Vidhya - CrowdAI - Numerai Follow @DrivenScience #DataScience #MachineLearning
11
3
Machine Learning Algorithms You Should Know: Supervised Learning | Common Algorithms: - Nearest Neighbor - Naive Bayes - Decision Trees - Linear Regression - Support Vector Machines (SVM) - Neural Networks Follow @DrivenScience #MachineLearning #Algorithms
2
19
58
9 Best Python libraries for Machine Learning - Numpy - Scipy - Scikit-learn - Theano - TensorFlow - Keras - PyTorch - Pandas - Matplotlib Follow @DrivenScience #MachineLearning #Python
2
34
1
61
“It is a capital mistake to theorize before one has data.” ~ Arthur Conan Doyle, Author of Sherlock Homes
1
3
Naive Bayes classifiers are a collection of classification algorithms based on Bayes’ Theorem. It is not a single but a family of algorithms with a common principle, i.e. every pair of features being classified is independent of each other. #MachineLearning #DataScience
1
4
“Without data you’re just another person with an opinion.” W. Edwards Deming, Statistician, Professor, Author, Lecturer, and Consultant
3
6
“Predicting the future isn’t magic, it’s artificial intelligence.” ~Dave Waters
5
11
3 ways to avoid Overfitting: 1. Cross-validation 2. Dimensionality reduction 3. Regularization
2
5
What is Overfitting in #MachineLearning: 👉 When a model captures "noise" instead of "signal" 👉 Hence, it performs impressively well on Training set, and poorly on Test set
1
6
3
“Artificial intelligence will reach human levels by around 2029. Follow that out further to, say, 2045, and we will have multiplied the intelligence – the human biological machine intelligence of our civilization – a billion-fold.” Ray Kurzweil, American inventor and futurist.
1
8
A multilayer perceptron (MLP) is a class of feedforward artificial neural network (ANN). Here's a diagrammatic representation of MLP👇 #MachineLearning #ArtificialIntelligence
2
10
Why are L1 and L2 regularisation methods used? 🤔 Both L1 and L2 regularization are methods used to reduce the overfitting of training data. #MachineLearning
2
7
“Some people call this artificial intelligence, but the reality is this technology will enhance us. So instead of artificial intelligence, I think we'll augment our intelligence.” —Ginni Rometty
1
5
When should you use matplotlib library for visualisation? 🤔 – Works well for simple bar charts, line charts, and scatterplots – Doesn't work well for elaborate interactive visualizations for the web
1
6
The goal of feature engineering is simply to make your data better suited to the problem at hand.
1
5
In Machine Learning, "features" are whatever inputs we provide to our model
2
4
What is a model? 👇 It’s simply a specification of a mathematical (or probabilistic) relationship that exists between different variables. #MachineLearning
1
4