wovepaper — the arXiv observatory

papers

Publications (34)

cs.CV2019

An Empirical Study of Batch Normalization and Group Normalization in Conditional Computation

Vincent Michalski, Vikram Voleti, Samira Ebrahimi Kahou +4

The paper empirically compares conditional batch normalization and conditional group normalization, examining their impact on generalization across visual question answering, few‑s…

Publications (34)

An Empirical Study of Batch Normalization and Group Normalization in Conditional Computation

Hierarchical Memory Networks

Recombinator Networks: Learning Coarse-to-Fine Feature Aggregation

Randomized Value Functions via Multiplicative Normalizing Flows

Convergent Tree Backup and Retrace with Function Approximation

EmoNets: Multimodal deep learning approaches for emotion recognition in video

A single NV defect coupled to a nanomechanical oscillator

Theano: A Python framework for fast computation of mathematical expressions

Adding noise to the input of a model trained with a regularized objective

Digital and FM demodulation of a doubly-clamped single wall carbon nanotube oscillator: towards a nanotube cell phone

Learning invariant features through local space contraction

Artificial Neural Networks Applied to Taxi Destination Prediction

Frequency modulated self-oscillation and phase inertia in a synchronized nanowire mechanical resonator

Role of fluctuations and nonlinearities on field emission nanomechanical self-oscillators

Reducing Uncertainty in Undersampled MRI Reconstruction with Active Acquisition

Universal Vectorial and Ultrasensitive Nanomechanical Force Field Sensor

Clustering is Efficient for Approximate Maximum Inner Product Search

Representation Learning: A Review and New Perspectives

Generalized Denoising Auto-Encoders as Generative Models

High-dimensional sequence transduction

GSNs : Generative Stochastic Networks

An Exploration of Softmax Alternatives Belonging to the Spherical Loss Family

Efficient Exact Gradient Update for training Deep Networks with Very Large Sparse Targets

Modeling Temporal Dependencies in High-Dimensional Sequences: Application to Polyphonic Music Generation and Transcription

Learning to Compute Word Embeddings On the Fly

Learning to Generate Samples from Noise through Infusion Training

Dropout as data augmentation

A Cheap Linear Attention Mechanism with Fast Lookups and Fixed-Size Representations

Exact gradient updates in time independent of output size for the spherical loss family

The Z-loss: a shift and scale invariant classification loss belonging to the Spherical Family

Bidimensional nano-optomechanics and topological backaction in a non-conservative radiation force field

A Generative Process for Sampling Contractive Auto-Encoders

Self-oscillations in field emission nanowire mechanical resonators: a nanometric DC-AC conversion

Improving Landmark Localization with Semi-Supervised Learning