PinnedYou Can Not Split The Atom In Your HeadTechnology Anxiety, or The importance of starting before we feel ready, and seeing what failsMay 28May 28
PinnedAI Adventures in The Library of BabelWould infinite books give us infinite knowledge?Apr 2, 2023Apr 2, 2023
PinnedPublished inEntrepreneur FirstThe Creation VocationReflections on founding a startup. Why you should create, and encourage others to create.Apr 2, 20185Apr 2, 20185
Published inDeeper LearningGlossary of Deep Learning: Batch NormalisationA technique for improving the performance and stability of neural networks.Jun 27, 20171Jun 27, 20171
Published inDeeper LearningGlossary of Deep Learning: AutoencoderAn Autoencoder is neural network capable of unsupervised feature learning.May 26, 2017May 26, 2017
Published inDeeper LearningGlossary of Deep Learning: Dynamic Memory NetworksA Dynamic Memory Network (DMN) is a refinement of the classic Seq2Seq architecture that adds an episodic memory.May 15, 2017May 15, 2017
Published inDeeper LearningGlossary of Deep Learning: ErrorIn learning, error is not a fault or failure, but a signal — an insight into how the accuracy of a model might be improved.Apr 26, 2017Apr 26, 2017
Published inDeeper LearningGlossary of Deep Learning: Word EmbeddingWord Embedding turns text into numbers, because learning algorithms expect continuous values, not strings.Apr 19, 20175Apr 19, 20175
Published inDeeper LearningGlossary of Deep Learning: BiasBias contributes to the output of a neuron, allowing the activation function to be shifted left or right, to better fit the data.Apr 14, 20173Apr 14, 20173
Published inDeeper LearningA Glossary of Deep LearningA notebook of deep learning concepts, carefully explained in simple language. Because complexity doesn’t need to be complicated.Apr 12, 20173Apr 12, 20173