Machine Learning Mondays #38: Every Monday I highlight an awesome ML paper that gets me pumped that I'm in this field! A important theoretical questions in deep learning is how deep models generalize, since they do not obey convergence laws of classical models; in particular, neural networks achieve better generalization as they become infinitely large (called overparametrization). Recent work in this area has suggested approaches that all depend on the uniform convergence of the model, an important property which gives bounds on convergence. In their NeurIPS 2019 Best New Directions paper, CMU researchers debate the validity of this approach and show that uniform convergence-based bounds cannot possibly "explain generalization". They first show that, in practice, these bounds increase with the dataset size, which is contrary to the theoretical prediction. Then, they provide several examples of overparametrized networks which have provably vacuous uniform convergence bounds.

The idea behind the BrainCraft board (stand-alone, and Pi "hat") is that you'd be able to "craft brains" for Machine Learning on the EDGE, with Microcontrollers & Microcomputers. On ASK AN ENGINEER, our founder & engineer chatted with Pete Warden, the technical lead of the mobile, embedded TensorFlow Group on Google's Brain team about what would be ideal for a board like this. We've started to design a BrainCraft HAT for Raspberry Pi and other linux computers. It has a 240 240 TFT display for inference output, slot for Camera connector cable for imaging projects, a 5 way joystick and button for UI input, left and right microphones, stereo headphone, stereo speaker out, three RGB dotstar LEDs, two 3 pin STEMMA connectors on PWM pins so they can drive NeoPixels or servos, and grove/stemma/qwiic I2C port. This should let people build a wide range of audio/video AI projects while also allowing easy plug in of sensors and robotics!

Out of the box, in less than 5 minutes, demonstrate and use Machine Learning (video). If you want to skip ahead to the demo-only, click here or scrub to: 4 mins, 50 secs. The idea behind the BrainCraft board (stand-alone, and Pi "hat") is that you'd be able to "craft brains" for Machine Learning on the EDGE, with Microcontrollers & Microcomputers. On ASK AN ENGINEER, our founder & engineer chatted with Pete Warden, the technical lead of the mobile, embedded TensorFlow Group on Google's Brain team about what would be ideal for a board like this. We've started to design a BrainCraft HAT for Raspberry Pi and other linux computers.

Cheat Sheet Posted on Monday, July 31st, 2017 at 12:16 pm. Share this: This blog post was authored by Vincent Xu. Vertica 8.1.1 provides SQL functions that support the complete machine learning workflow--from cleaning your data to training a model to evaluating model performance. Vertica machine learning is fast and scalable along the sizes of data samples, features, and computing cluster. Best of all, no data movement is necessary.