In previous posts (here and here), deep Q reinforcement learning was introduced. In these posts, examples were presented where neural networks were used to train an agent to act within an environment to maximize rewards.… Read More »Double Q reinforcement learning in TensorFlow 2
In this post, I’m going to cover the very important deep learning concept called transfer learning. Transfer learning is the process whereby one uses neural network models trained in a related domain to accelerate the development… Read More »Transfer learning in TensorFlow 2 tutorial
For those familiar with convolutional neural networks (if you’re not, check out this post), you will know that, for many architectures, the final set of layers are often of the fully connected variety. This is… Read More »An introduction to Global Average Pooling in convolutional neural networks
In this relatively short post, I’m going to show you how to deal with metrics and summaries in TensorFlow 2. Metrics, which can be used to monitor various important variables during the training of deep… Read More »Metrics and summaries in TensorFlow 2
If you’ve been involved with neural networks and have beeen using them for classification, you almost certainly will have used a cross entropy loss function. However, have you really understood what cross-entropy means? Do you… Read More »An introduction to entropy, cross entropy and KL divergence in machine learning
It’s a great time to be practising deep learning. The main existing deep learning frameworks like TensorFlow, Keras and PyTorch are maturing and offer a lot of functionality to streamline the deep learning process. There are also other great tool sets emerging for the deep learning practitioner. One of these is the Google Colaboratory environment.… Read More »Google Colaboratory introduction – Learn how to build deep learning systems in Google Colaboratory
A recent announcement from the TensorFlow development team has informed the world that some major new changes are coming to TensorFlow, resulting in a new major version TensorFlow 2.0. The three biggest changes include: TensorFlow Eager execution to be standard The cleaning up of a lot of redundant APIs The removal of tf.contrib with select… Read More »Keras, Eager and TensorFlow 2.0 – a new TF paradigm
Deep learning can be complicated…and sometimes frustrating. Why is my lousy 10 layer conv-net only achieving 95% accuracy on MNIST!? We’ve all been there – something is wrong and it can be hard to figure out why. Often the best solution to a problem can be found by visualizing the issue. This is why TensorFlow’s… Read More »Introduction to TensorBoard and TensorFlow visualization
TensorFlow is a great deep learning framework. In fact, it is still the reigning monarch within the deep learning framework kingdom. However, it has some frustrating limitations. One of these is the difficulties that arise during debugging. In TensorFlow, it’s difficult to diagnose what is happening in your model. This is due to its static graph… Read More »TensorFlow Eager tutorial
Reinforcement learning has gained significant attention with the relatively recent success of DeepMind’s AlphaGo system defeating the world champion Go player. The AlphaGo system was trained in part by reinforcement learning on deep neural networks. This type of learning is a different aspect of machine learning from the classical supervised and unsupervised paradigms. In reinforcement… Read More »Reinforcement learning tutorial with TensorFlow