conftrace_
← Architectures
Deep Learning › Architectures ›

Neural Networks

11,300 papers

Papers per year

Papers

Beyond Finite Layer Neural Networks: Bridging Deep Architectures and Numerical Differential Equations ICML 2018
The Power of Interpolation: Understanding the Effectiveness of SGD in Modern Over-parametrized Learning ICML 2018
Dimensionality-Driven Learning with Noisy Labels ICML 2018
Bounds on the Approximation Power of Feedforward Neural Networks ICML 2018
Training Neural Machines with Trace-Based Supervision ICML 2018
Differentiable Abstract Interpretation for Provably Robust Neural Networks ICML 2018
DICOD: Distributed Convolutional Coordinate Descent for Convolutional Sparse Coding ICML 2018
Kernelized Synaptic Weight Matrices ICML 2018
Optimization Landscape and Expressivity of Deep CNNs ICML 2018
Neural Networks Should Be Wide Enough to Learn Disconnected Decision Regions ICML 2018
Functional Gradient Boosting based on Residual Network Perception ICML 2018
Learning Compact Neural Networks with Regularization ICML 2018
Gradually Updated Neural Networks for Large-Scale Image Recognition ICML 2018
DCFNet: Deep Neural Network with Decomposed Convolutional Filters ICML 2018
Spurious Local Minima are Common in Two-Layer ReLU Neural Networks ICML 2018
Bounding and Counting Linear Regions of Deep Neural Networks ICML 2018
Differentiable Compositional Kernel Learning for Gaussian Processes ICML 2018
Neural Inverse Rendering for General Reflectance Photometric Stereo ICML 2018
Learning Longer-term Dependencies in RNNs with Auxiliary Losses ICML 2018
Invariance of Weight Distributions in Rectified MLPs ICML 2018
Online Convolutional Sparse Coding with Sample-Dependent Dictionary ICML 2018
Extracting Automata from Recurrent Neural Networks Using Queries and Counterexamples ICML 2018
Deep Predictive Coding Network for Object Recognition ICML 2018
Dynamical Isometry and a Mean Field Theory of CNNs: How to Train 10,000-Layer Vanilla Convolutional Neural Networks ICML 2018
Stabilizing Gradients for Deep Neural Networks via Efficient SVD Parameterization ICML 2018