Pytorch

Reinforcement learning is my area of focus so far when it comes to deep learning. RL is probably not the first stop for most on the machine learning education circuit, but it just happens to be where the problem I am trying to solve has taken me. When starting down the RL road, I was immediately confused by the concept of reward. Nothing was confusing about what it was - giving a dog a treat when it sits after you’ve asked it to sums things up pretty well. Instead, I was confused by its relation to the loss function. Both, at a high level, help inform when the correct thing is happening. ...

My journey into machine learning is still in its relatively early stages. I began by familiarizing myself with Tensorflow. It was an excellent introduction, whetting my appetite for AI, but I am now ready to make the switch to PyTorch. There are two key drivers behind my decision to make this change. Debugging Process transparency Debugging Debugging in Tensorflow has been problematic, to say the least, being most painful when writing custom loss functions. I’d feed dummy data to the loss function while writing it, pre-vetting what I was creating. However, when something didn’t work as expected during training, troubleshooting was near impossible. Tensors at training time are opaque, acting in some “virtual” fashion if my memory serves (this was a while ago now). ...