
A CharacterWord Compositional Neural Language Model for Finnish
Inspired by recent research, we explore ways to model the highly morphol...
read it

SemiSupervised Domain Adaptation for Weakly Labeled Semantic Video Object Segmentation
Deep convolutional neural networks (CNNs) have been immensely successful...
read it

Ladder Variational Autoencoders
Variational Autoencoders are powerful models for unsupervised learning. ...
read it

SemiSupervised Learning with Ladder Networks
We combine supervised learning with unsupervised learning in deep neural...
read it

DopeLearning: A Computational Approach to Rap Lyrics Generation
Writing rap lyrics requires both creativity to construct a meaningful, i...
read it

Lateral Connections in Denoising Autoencoders Support Supervised Learning
We show how a deep denoising autoencoder with lateral connections can be...
read it

Bidirectional Recurrent Neural Networks as Generative Models  Reconstructing Gaps in Time Series
Bidirectional recurrent neural networks (RNN) are trained to predict bot...
read it

Denoising autoencoder with modulated lateral connections learns invariant representations of natural images
Suitable lateral connections between encoder and decoder are shown to al...
read it

Linear StateSpace Model with TimeVarying Dynamics
This paper introduces a linear statespace model with timevarying dynam...
read it

Techniques for Learning Binary Stochastic Feedforward Neural Networks
Stochastic binary hidden units in a multilayer perceptron (MLP) network...
read it

Stochastic Gradient Estimate Variance in Contrastive Divergence and Persistent Contrastive Divergence
Contrastive Divergence (CD) and Persistent Contrastive Divergence (PCD) ...
read it

Pushing Stochastic Gradient towards SecondOrder Methods  Backpropagation Learning with Transformations in Nonlinearities
Recently, we proposed to transform the outputs of each hidden neuron in ...
read it

Bayes Blocks: An Implementation of the Variational Bayesian Building Blocks Framework
A software library for constructing and learning probabilistic models is...
read it

'Say EM' for Selecting Probabilistic Models for Logical Sequences
Many real world sequences such as protein secondary structures or shell ...
read it

SemiSupervised Anomaly Detection  Towards ModelIndependent Searches of New Physics
Most classification algorithms used in high energy physics fall under th...
read it
Tapani Raiko
is this you? claim profile
Principal Research Scientist at Apple Inc. since 2016, Project Leader/Scientist of Deep Learning and Bayesian Modelling research group in Aalto University School of Science, Cofounder at The Curious AI Company from 20152016, Academy Research Fellow at Aalto University from 20142016, Assistant Professor at Aalto University from 20142016, Visiting Assistant Professor at Université de Montréal 2014, Senior Scientist at ZenRobotics Ltd from 20092014, Postdoctoral Researcher at Aalto University from 20062014, Visiting Researcher at University of Toronto 2012, Visiting Researcher at New York University 2010, Postgraduate Researcher at Helsinki University of Technology / Laboratory of Computer and Information Science from 20022006.