Corpus ID: 38785151

Knet : beginning deep learning with 100 lines of

@inproceedings{Yuret2016KnetB,
  title={Knet : beginning deep learning with 100 lines of},
  author={Julia Deniz Yuret},
  year={2016}
}
Knet (pronounced "kay-net") is the Koç University machine learning framework implemented in Julia, a high-level, high-performance, dynamic programming language. Unlike gradient generating compilers like Theano and TensorFlow which restrict users into a modeling mini-language, Knet allows models to be defined by just describing their forward computation in plain Julia, allowing the use of loops, conditionals, recursion, closures, tuples, dictionaries, array indexing, concatenation and other high… Expand
Fast multidimensional reduction and broadcast operations on GPU for machine learning
TLDR
This work proposes two new strategies that extend the existing implementations to perform on tensors for scalar reduction and broadcast and introduces formal definitions of both operations using tensor notations, investigate their mathematical properties, and exploit these properties to provide an efficient solution for each. Expand
TYPE FastMultidimensional Reduction and Broadcast Operations on GPU forMachine Learning
Present Address Koç University, Rumelifeneri Yolu, Sarıyer, Istanbul, Turkey, 34450 Summary Reduction and broadcast operations are commonly used in machine learning algorithms for different purposes.Expand
Parsing with Context Embeddings
We introduce context embeddings, dense vectors derived from a language model that represent the left/right context of a word instance, and demonstrate that context embeddings significantly improveExpand
TensorFlow.jl: An Idiomatic Julia Front End for TensorFlow
TLDR
TensorFlow.jl is a Julia client library for the TensorFlow deep-learning framework that allows users to define Tensor Flow graphs using Julia syntax, which are interchangeable with the graphs produced by Google’s first-party Python Tensorflow client and can be used to perform training or inference on machine-learning models. Expand
Morphological Analysis Using a Sequence Decoder
TLDR
Morse, a recurrent encoder-decoder model that produces morphological analyses of each word in a sentence is introduced and it is shown that generating morphological features individually rather than as a combined tag allows the model to handle rare or unseen tags and to outperform whole-tag models. Expand
Graph Tracking in Dynamic Probabilistic Programs via Source Transformations
TLDR
Many machine learning methods acting on graph structures can be expressed in terms of message passing, among them variational methods for approximate Bayesian inference, automatic differentiation (AD), and backpropagation. Expand
Multidimensional Broadcast Operation on the GPU
Broadcast is a common operation in machine learning and widely used in calculating bias or subtracting maximum for normalization in convolutional neural networks. Broadcast operation is required whenExpand
Learning Sparse Neural Networks via Sensitivity-Driven Regularization
TLDR
This work quantifies the output sensitivity to the parameters and introduces a regularization term that gradually lowers the absolute value of parameters with low sensitivity, so that a very large fraction of the parameters approach zero and are eventually set to zero by simple thresholding. Expand
Partially Exchangeable Networks and Architectures for Learning Summary Statistics in Approximate Bayesian Computation
TLDR
A novel family of deep neural architectures, named partially exchangeable networks (PENs) that leverage probabilistic symmetries and employ PENs to learn summary statistics in approximate Bayesian computation (ABC). Expand
SParse: Koç University Graph-Based Parsing System for the CoNLL 2018 Shared Task
TLDR
Sarse, the Graph-Based Parsing model submitted for the CoNLL 2018 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies, extends the state-of-the-art biaffine parser with a structural meta-learning module, SMeta, that combines local and global label predictions. Expand
...
1
2
3
4
...

References

SHOWING 1-10 OF 18 REFERENCES
Theano: A Python framework for fast computation of mathematical expressions
TLDR
The performance of Theano is compared against Torch7 and TensorFlow on several machine learning models and recently-introduced functionalities and improvements are discussed. Expand
TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
TLDR
The TensorFlow interface and an implementation of that interface that is built at Google are described, which has been used for conducting research and for deploying machine learning systems into production across more than a dozen areas of computer science and other fields. Expand
Torch7: A Matlab-like Environment for Machine Learning
TLDR
Torch7 is a versatile numeric computing framework and machine learning library that extends Lua that can easily be interfaced to third-party software thanks to Lua’s light interface. Expand
Caffe: Convolutional Architecture for Fast Feature Embedding
TLDR
Caffe provides multimedia scientists and practitioners with a clean and modifiable framework for state-of-the-art deep learning algorithms and a collection of reference models for training and deploying general-purpose convolutional neural networks and other deep models efficiently on commodity architectures. Expand
Long Short-Term Memory
TLDR
A novel, efficient, gradient based method called long short-term memory (LSTM) is introduced, which can learn to bridge minimal time lags in excess of 1000 discrete-time steps by enforcing constant error flow through constant error carousels within special units. Expand
Automatic differentiation in machine learning: a survey
TLDR
By precisely defining the main differentiation techniques and their interrelationships, this work aims to bring clarity to the usage of the terms “autodiff’, “automatic differentiation”, and “symbolic differentiation" as these are encountered more and more in machine learning settings. Expand
Very Deep Convolutional Networks for Large-Scale Image Recognition
TLDR
This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers. Expand
Gradient-based learning applied to document recognition
TLDR
This paper reviews various methods applied to handwritten character recognition and compares them on a standard handwritten digit recognition task, and Convolutional neural networks are shown to outperform all other techniques. Expand
Julia: A Fresh Approach to Numerical Computing
TLDR
The Julia programming language and its design is introduced---a dance between specialization and abstraction, which recognizes what remains the same after computation, and which is best left untouched as they have been built by the experts. Expand
Learning and Stochastic Approximations 3 Q ( z , w ) measures the economical cost ( in hard currency units ) of delivering
The convergence of online learning algorithms is analyzed using the tools of the stochastic approximation theory, and proved under very weak conditions. A general framework for online learningExpand
...
1
2
...