Search Results for author:
Found 21 papers, 7 papers with code
Annotated History of Modern AI and Deep Learning
Machine learning is the science of credit assignment: finding patterns in observations that predict the consequences of actions and help to improve future performance.
Deep Learning: Our Miraculous Year 1990-1991
In 2020-2021, we celebrated that many of the basic ideas behind the deep learning revolution were published three decades ago within fewer than 12 months in our "Annus Mirabilis" or "Miraculous Year" 1990-1991 at TU Munich.
Reinforcement Learning Upside Down: Don't Predict Rewards -- Just Map Them to Actions
UDRL generalizes to achieve high rewards or other goals, through input commands such as: get lots of reward within at most so much time!
Generative Adversarial Networks are Special Cases of Artificial Curiosity (1990) and also Closely Related to Predictability Minimization (1991)
I review unsupervised or self-supervised neural networks playing minimax games in game-theoretic settings: (i) Artificial Curiosity (AC, 1990) is based on two such networks.
Improving Differentiable Neural Computers Through Memory Masking, De-allocation, and Link Distribution Sharpness Control
The Differentiable Neural Computer (DNC) can learn algorithmic and question answering tasks.
Investigations on End-to-End Audiovisual Fusion
Audiovisual speech recognition (AVSR) is a method to alleviate the adverse effect of noise in the acoustic signal.
One Big Net For Everything
Then ONE is retrained in PowerPlay style (2011) on stored input/output traces of (a) ONE's copy executing the new skill and (b) previous instances of ONE whose skills are still considered worth memorizing.
Hindsight policy gradients
A reinforcement learning agent that needs to pursue different goals across episodes requires a goal-conditional policy.
Improving Speaker-Independent Lipreading with Domain-Adversarial Training
We present a Lipreading system, i. e. a speech recognition system using only visual features, which uses domain-adversarial training for speaker independence.
On Learning to Think: Algorithmic Information Theory for Novel Combinations of Reinforcement Learning Controllers and Recurrent Neural World Models
The basic ideas of this report can be applied to many other cases where one RNN-like system exploits the algorithmic information content of another.
Parallel Multi-Dimensional LSTM, With Application to Fast Biomedical Volumetric Image Segmentation
In contrast, Multi-Dimensional Recurrent NNs (MD-RNNs) can perceive the entire spatio-temporal context of each pixel in a few sweeps through all pixels, especially when the RNN is a Long Short-Term Memory (LSTM).
Deep Networks with Internal Selective Attention through Feedback Connections
It harnesses the power of sequential processing to improve classification performance, by allowing the network to iteratively focus its internal attention on some of its convolutional filters.
Ranked #181 on
Image Classification
on CIFAR-10
Deep Learning in Neural Networks: An Overview
In recent years, deep artificial neural networks (including recurrent ones) have won numerous contests in pattern recognition and machine learning.
Testing Hypotheses by Regularized Maximum Mean Discrepancy
Do two data samples come from different distributions?
Multi-column Deep Neural Networks for Image Classification
Traditional methods of computer vision and machine learning cannot match human performance on tasks such as the recognition of handwritten digits or traffic signs.
Ranked #7 on
Image Classification
on MNIST
Deep Big Simple Neural Nets Excel on Handwritten Digit Recognition
Good old on-line back-propagation for plain multi-layer perceptrons yields a very low 0. 35% error rate on the famous MNIST handwritten digits benchmark.
Driven by Compression Progress: A Simple Principle Explains Essential Aspects of Subjective Beauty, Novelty, Surprise, Interestingness, Attention, Curiosity, Creativity, Art, Science, Music, Jokes
I argue that data becomes temporarily interesting by itself to some self-improving, but computationally limited, subjective observer once he learns to predict or compress the data in a better way, thus making it subjectively simpler and more beautiful.
Multi-Dimensional Recurrent Neural Networks
Recurrent neural networks (RNNs) have proved effective at one dimensional sequence learning tasks, such as speech and online handwriting recognition.
New Millennium AI and the Convergence of History
Artificial Intelligence (AI) has recently become a real formal science: the new millennium brought the first mathematically sound, asymptotically optimal, universal problem solvers, providing a new, rigorous foundation for the previously largely heuristic field of General AI and embedded agents.
Algorithmic Theories of Everything
The probability distribution P from which the history of our universe is sampled represents a theory of everything or TOE.
A Computer Scientist's View of Life, the Universe, and Everything
Is the universe computable?
Quantum Physics Computational Complexity Computers and Society Computational Physics Popular Physics
