Search Results for author:
Found 12 papers, 3 papers with code
DDD20 End-to-End Event Camera Driving Dataset: Fusing Frames and Events with Deep Learning for Improved Steering Prediction
The dataset was captured with a DAVIS camera that concurrently streams both dynamic vision sensor (DVS) brightness change events and active pixel sensor (APS) intensity frames.
Interpretable Graph Convolutional Neural Networks for Inference on Noisy Knowledge Graphs
In this work, we provide a new formulation for Graph Convolutional Neural Networks (GCNNs) for link prediction on graph data that addresses common challenges for biomedical knowledge graphs (KGs).
PRED18: Dataset and Further Experiments with DAVIS Event Camera in Predator-Prey Robot Chasing
Conventional vision CNNs are driven by camera frames at constant sample rate, thus achieving a fixed latency and power consumption tradeoff.
Exploring Deep Recurrent Models with Reinforcement Learning for Molecule Design
The design of small molecules with bespoke properties is of central importance to drug discovery.
ADaPTION: Toolbox and Benchmark for Training Convolutional Neural Networks with Reduced Numerical Precision Weights and Activation
Using the ADaPTION tools, we quantized several CNNs including VGG16 down to 16-bit weights and activations with only 0. 8% drop in Top-1 accuracy.
DDD17: End-To-End DAVIS Driving Dataset
Event cameras, such as dynamic vision sensors (DVS), and dynamic and active-pixel vision sensors (DAVIS) can supplement other autonomous driving sensors by providing a concurrent stream of standard active pixel sensor (APS) images and DVS temporal contrast events.
Sensor Transformation Attention Networks
Recent work on encoder-decoder models for sequence-to-sequence mapping has shown that integrating both temporal and spatial attention mechanisms into neural networks increases the performance of the system substantially.
Delta Networks for Optimized Recurrent Network Computation
Similarly, on the large Wall Street Journal speech recognition benchmark even existing networks can be greatly accelerated as delta networks, and a 5. 7x improvement with negligible loss of accuracy can be obtained through training.
Phased LSTM: Accelerating Recurrent Network Training for Long or Event-based Sequences
In this work, we introduce the Phased LSTM model, which extends the LSTM unit by adding a new time gate.
Steering a Predator Robot using a Mixed Frame/Event-Driven Convolutional Neural Network
The CNN is trained and run on data from a Dynamic and Active Pixel Sensor (DAVIS) mounted on a Summit XL robot (the predator), which follows another one (the prey).
Precise neural network computation with imprecise analog devices
The operations used for neural network computation map favorably onto simple analog circuits, which outshine their digital counterparts in terms of compactness and efficiency.
A Curriculum Learning Method for Improved Noise Robustness in Automatic Speech Recognition
The performance of automatic speech recognition systems under noisy environments still leaves room for improvement.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
