"I only take issue with one or two things:
"A good data scientist is a bad coder"
There is no excuse for being a bad coder. Incapable? That's fine. But a bad coder is a lazy coder - poor style, useless comments, etc.."
L.V.'s Discussions
Question about connected cars
Started this discussion. Last reply by Page Schorer May 19, 2016. 1 Reply 0 Likes
With automated cars communicating with each other (machine-to-machine communications - thus the word connected cars), could we envision the following futurist scenario:Cars exchange their…Continue
Book: Deep Learning With Python
Started this discussion. Last reply by Patrick J. Hagan Jun 30, 2016. 1 Reply 4 Likes
From First Model, To State-of-the-Art ResultsDeep learning is the most interesting and powerful machine learning technique right now.Top deep learning libraries are available on the Python ecosystem…Continue
Kaggle Releases Data Sets About Global Warming: Make your own Predictions
Started Apr 13, 2016 0 Replies 0 Likes
Analyze the data, make your own conclusions about global warming and climate change (especially predictions), and post your results in the comment section below: this article will be featured and…Continue
Book: Mastering Python for Data Science
Started this discussion. Last reply by Patrick J. Hagan Jun 30, 2016. 1 Reply 5 Likes
About This BookMaster data science methods using Python and its librariesCreate data visualizations and mine for patternsAdvanced techniques for the four fundamentals of Data Science with Python -…Continue
Gifts Received
L.V. has not received any gifts yet
L.V.'s Page
Latest Activity
"There a lot of conditions which influence of the salary level. On the one hand it's so easy to find good job with desire level, if you have high level of quality, all necessary skills. But on the other hand (for instance python entwickler…"
Profile Information
- Professional Status
- Other
- Your Job Title:
- Data Analyst
- Interests:
- Other
L.V.'s Blog
Deep Learning Networks: Advantages of ReLU over Sigmoid Function
Posted on October 11, 2018 at 6:00pm 0 Comments 1 Like
This was posted as a question on StackExchange. The state of the art of non-linearity is to use rectified linear units (ReLU) instead of sigmoid function in deep neural network. What are the advantages? I know that training a network when ReLU is used would be faster, and it is more biological inspired, what are the other advantages? (That is, any disadvantages of using sigmoid)?…
ContinueDeep Learning: AlphaGo Zero Explained In One Picture
Posted on January 4, 2018 at 6:00pm 1 Comment 8 Likes
Recently Google DeepMind announced AlphaGo Zero — an extraordinary achievement that has shown how it is possible to train an agent to a superhuman level in the highly complex and challenging domain of Go, ‘tabula rasa’ — that is, from a blank slate, with no human expert play used as training data.
It thrashed the previous reincarnation 100–0, using only 4TPUs instead of 48TPUs and a single…
ContinueChoosing the Correct Type of Regression Analysis
Posted on January 4, 2018 at 6:00pm 0 Comments 5 Likes
Book: Machine Learning: a Probabilistic Perspective
Posted on November 15, 2017 at 6:00pm 1 Comment 4 Likes
Today’s Web-enabled deluge of electronic data calls for automated methods of data analysis. Machine learning provides these, developing methods that can automatically detect patterns in data and then use the uncovered patterns to predict future data. This textbook offers a comprehensive and self-contained introduction to the field of machine learning, based on a unified, probabilistic approach.
The coverage combines breadth and depth, offering necessary…
Comment Wall
- No comments yet!
Resources
Videos
© 2020 Data Science Central ®
Powered by
Badges | Report an Issue | Privacy Policy | Terms of Service
