top of page
Search

Use of a short list

(20th-Nov-2020) Hierarchical Softmax • A classical approach ( , ) to reducing the computational burden Goodman 2001 of high-dimensional...

High-Dimensional Outputs

(19teen-Nov-2020) • In many natural language applications, we often want our models to produce words (rather than characters) as the...

Neural Language Models

(18teen-Nov-2020) Neural language models or NLMs are a class of language model designed to overcome the curse of dimensionality problem...

Natural Language Processing

(17teen-Nov-2020) • Natural language processing (NLP) is the use of human languages, such as English or French, by a computer. Computer...

Dataset Augmentation

(16th-Nov-2020) • As described in section , it is easy to improve the generalization of a classifier 7.4 by increasing the size of the...

Contrast Normalization

(14th-Nov-2020) • Suppose we have an image represented by a tensor X ∈Rr c ××3, with Xi,j,1 being the red intensity at row i and column...

Preprocessing

(13th-Nov-2020) • Many application areas require sophisticated preprocessing because the original input comes in a form that is difficult...

Model Compression

(11th-Nov-2020) • In many commercial applications, it is much more important that the time and memory cost of running inference in a...

GPU Implementations

(10th-Nov-2020) • Most modern neural network implementations are based on graphics processing units. Graphics processing units (GPUs) are...

Deep Learning Applications

(9th-Nov-2020) • How to use deep learning to solve applications in computer vision, speech recognition, natural language processing, and...

Example of Neuron

(8th-Nov-2020) Some of Neuron application are following such as Playing Go and self driving car.

Neuron

(7th-Nov-2020)

Multilayer Neural Networks

(5th-Nov-2020) • Deeper architecture is more expressive than a shallow one – 1-layer nets only model linear hyper planes – 2-layer nets...

Classification:Sigmoidneurons

(4th-Nov-2020) These give a real-valued output that is a smoothand bounded function. • They have nice derivatives which make learning...

Reasons to study neural computation

(2nd-Nov-2020) To understand how the brain actually works. – Its very big and very complicated and made of stuff that dies when you poke...

Other goals for unsupervised learning

(1st-Nov-2020) It provides a compact, low-dimensional representation of the input. – High-dimensional inputs typically live on or near a...

bottom of page