In this talk from NodeConf EU 2017, Nikhila Ravi explains the advantages of client-side machine learning vs. server-side machine learning.
Since I started doing Data Science a few years ago, I have used more advanced mathematics than I ever thought I would have. And, as I take the DeepLearning.ai classes, that use of mathematics has accelerated.
Given that the math side of Data Science and AI is not going away any time soon, it’s probably best to get good at it.
Fortunately, for all of us Siraj Raval explains how to read math equations in a way that only he can: quickly and awesomely.
In this video, Siraj Raval talks about the technology behind Human Pose Estimation. This technology can, among other things, convert humans depicted in video to 3D models.
Think of what this means for motion capture.
Artificial Intelligence has transformed vision technology! Carl and Richard talk to Tim Huckaby about his latest work with vision systems for retail, security and more. Tim talks about how AI has fundamentally changed the way you implement vision systems, taking away many of the limitations on number of people tracked, object and face recognition and so on. The conversation digs into the demonstration done at the Build conference for using regular security cameras to implement a real-time safety tracking system on a construction site – aspirational, but coming soon! And of course, there’s a long conversation about privacy. What is fair, reasonable and wise?
Listen Now –>
Siraj Raval has a great talk on genetic algorithms and neuroevolutionary strategies offer us a way to replicate the process of natural selection en silico. (Bonus points for the Latin usage, Siraj!)
Google already uses self-creating AI as part of its AutoML service that finds the best model for customers.
In this episode of the AI show Erika explains how to create deep learning models with music as the input. She begins by describing the problem of generating music by specifically describing how she generated the appropriate features from a midi file. She then describes the deep learning model she used in order to generate music.
Microsoft Research posted this video of Sumit Gulwani, who founded the PROSE research and engineering team at Microsoft. This team develops programming-by-example (PBE) APIs and ships them through multiple Microsoft products.
PBE is a new frontier in AI wherein the computer programs itself—the user provides input-output examples and the computer synthesizes an intended script. This is significant because 99% of computer users do not know programming. Even for programmers, this can provide a 10-100x productivity increase for many task domains.
A killer application of PBE is in the space of data cleaning/preparation since data scientists often spend up to 80% time wrangling data into a form suitable for learning models or drawing insights. In this video, Sumit illustrates how a data cleaning task, that Python programmers took an average of 30 minutes to finish, can be performed in 30 seconds by non-programmers using the PBE paradigm. In particular, PBE can help ingest a file into tabular format, split a column to extract constituent sub-fields, derive new columns, and suggest form entries.
TensorFlow is a powerful data flow-oriented machine learning framework developed by Google’s Brain Team. It was designed to be easy to use and widely applicable on both numeric, neural network-oriented problems as well as other domains.