Deep learning can be a complex and daunting field for newcomers.

Concepts like hidden layers, convolutional neural networks, backpropagation keep coming up as you try to grasp deep learning topics. Most people are put off of the math alone.

Despite what you have been led to believe, you don’t need an advanced degree or a Ph.D. to learn and master deep learning.

There are certain key concepts you should know (and be well versed in) before you plunge too far into the deep learning world.

The five essentials for starting your deep learning journey are:

  1. Getting your system ready
  2. Python programming
  3. Linear Algebra and Calculus
  4. Probability and Statistics
  5. Key Machine Learning Concepts

Lex Fridman interviews Lee Smolin, a theoretical physicist, co-inventor of loop quantum gravity, and a contributor of many interesting ideas to cosmology, quantum field theory, the foundations of quantum mechanics, theoretical biology, and the philosophy of science.

He is the author of several books including one that critiques the state of physics and string theory called The Trouble with Physics, and his latest book, Einstein’s Unfinished Revolution: The Search for What Lies Beyond the Quantum.

This conversation is part of the Artificial Intelligence podcast. 

Time Stamps:

  • 0:00 – Introduction
  • 3:03 – What is real?
  • 5:03 – Scientific method and scientific progress
  • 24:57 – Eric Weinstein and radical ideas in science
  • 29:32 – Quantum mechanics and general relativity
  • 47:24 – Sean Carroll and many-worlds interpretation of quantum mechanics
  • 55:33 – Principles in science
  • 57:24 – String theory

Jon Wood shows the new models you can build with the updated ML.NET Model Builder in this video.

Related Links:

Quantum computing is still in at the early stage. However, the technology is maturing rapidly.

To take advantage of tomorrow’s ultra-fast quantum machines, researchers will have to write specialized algorithms that can run on qubits instead of bits, and they’ll need equally specialized development tools to help with the task.

That’s where TensorFlow Quantum comes into the picture. It provides a set of operators, low-level programming building blocks, for creating AI models that work with qubits, quantum logic gates and quantum circuits. These operators abstract away some of the underlying complexity to reduce the amount of code researchers need to write.