File list
Jump to navigation
Jump to search
This special page shows all uploaded files.
| Date | Name | Thumbnail | Size | User | Description | Versions |
|---|---|---|---|---|---|---|
| 23:31, 4 November 2018 | Fader et al 2014 Fig1.png (file) | 51 KB | Omoreira | Figure 1: OQA automatically mines millions of operators (left) from unlabeled data, then learns to compose them to answer questions (right) using evidence from multiple knowledge bases. In: Anthony Fader, [[Luke Zet... | 1 | |
| 23:51, 28 October 2018 | diags-figure1.png (file) | 32 KB | Omoreira | 1 | ||
| 23:50, 28 October 2018 | diags-figure0.png (file) | 7 KB | Omoreira | 1 | ||
| 23:24, 28 October 2018 | Jurasky Martin 2018 Chap9 Fig5.png (file) | 22 KB | Omoreira | <B>Figure 9.5</B> Forward inference in a simple recurrent network. In:Daniel Jurafsky, and James H. Martin (2018). [https://web.stanford.edu/~jurafsky/slp3/9.pdf "Chapter 9 -- Sequence Processing with Recurrent Networks"]. In: [https:/... | 1 | |
| 23:20, 28 October 2018 | Jurasky Martin 2018 Chap9 Fig4.png (file) | 38 KB | Omoreira | <B>Figure 9.4</B> A simple recurrent neural network shown unrolled in time. Network layers are copied for each timestep, while the weights <i>U</i>, <i>V</i> and <i>W</i> are shared in common across all timesteps. In: [[Da... | 1 | |
| 15:51, 28 October 2018 | Ting et al 2017 LWRControl Fig1.png (file) | 103 KB | Omoreira | .In: Jo-Anne Ting, Franzisk Meier, Sethu Vijayakumar, and Stefan Schaal (2017) [https://link.springer.com/referenceworkentry/10.1007/978-1-4899-7687-1_493 "Locally Weighted Regression for Control"]. In: Sammut & Webb (2017). <P><B>... | 1 | |
| 20:59, 21 October 2018 | Jurafsky Martin 2018 Chap9 Fig14.png (file) | 29 KB | Omoreira | Figure 9.14 Basic neural units used in feed-forward, simple recurrent networks (SRN), long short-term memory (LSTM) and gate recurrent units. In: Daniel Jurafsky, and James H. Martin (2018). [https://web.stanford.edu/~juraf... | 1 | |
| 04:36, 20 October 2018 | Smith 2017 Fig2.png (file) | 37 KB | Omoreira | Figure 2. Triangular learning rate policy. The blue lines represent learning rate values changing between bounds. The input parameter stepsize is the number of iterations in half a cycle. In: Leslie N. Smith (2017, March). [http... | 1 | |
| 22:00, 14 October 2018 | D2AG LSTM.png (file) | 67 KB | Omoreira | Figure 3: D2AG-LSTM In: Zemin Liu, Vincent W. Zheng, Zhou Zhao, Fanwei Zhu, Kevin Chen-Chuan Chang, Minghui Wu, and Jing Ying (2018). [http://forward.cs.illinois.edu/pubs/2017/dagembed-aaai2018-lzzzcwy-201711.pdf "Distan... | 1 | |
| 21:21, 14 October 2018 | Shuai 1026 DAG RNN Fig3.png (file) | 62 KB | Omoreira | Figure 3: The architecture of the full labeling network, which consists of three functional layers: (1), convolution layer: it produces discriminative feature maps; (2), DAG-RNN: it models the [[conte... | 1 | |
| 20:42, 14 October 2018 | DAG LSTM.png (file) | 68 KB | Omoreira | Figure 1: An example of DAG-LSTM in modeling a sentence. Nodes with different colors contain different types of LSTM memory blocks. In: Xiaodan Zhu, Parinaz Sobhani, and Hongyu Guo (2016). [http://www.aclweb.org/anthology/N1... | 1 | |
| 17:33, 14 October 2018 | Goller Kuchler 1996 Fig2.png (file) | 22 KB | Omoreira | Figure 2: Tree and DAG representation of a set of terms. In: Christoph Goller, and Andreas Kuchler (1996). [http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.49.1968&rep=rep1&type=pdf "Learning task-dependent distributed represen... | 1 | |
| 23:00, 7 October 2018 | SequeezeNet Architeture.png (file) | 86 KB | Omoreira | Figure 2: Macroarchitectural view of our SqueezeNet architecture. Left: SqueezeNet (Section 3.3); Middle: SqueezeNet with simple bypass (Section 6); Right: SqueezeNet with complex bypass (Section 6). In:Forrest N. Iandola, [[Song Ha... | 1 | |
| 23:00, 7 October 2018 | SqueezeNet FireModule.png (file) | 56 KB | Omoreira | Figure 1: Microarchitectural view: Organization of convolution filters in the Fire module. In this example, s1x1 = 3, e1x1 = 4, and e3x3 = 4. We illustrate the convolution filters but not the activations. In: Forrest N. Iandola, [[S... | 1 | |
| 23:51, 30 September 2018 | Resnet He 2015 Fig3.png (file) | 164 KB | Omoreira | <P>Figure 3. Example network architectures for ImageNet. Left: the VGG-19 model(19.6 billion FLOPs) as a reference. Middle: a plain network with 34 parameter layers (3.6 billion FLOPs). Right: a residual network with 34 parameter layers... | 1 | |
| 22:30, 30 September 2018 | GoogLeNet slide58.png (file) | 185 KB | Omoreira | Slide 58. In: Fei-Fei Li, Justin Johnson, and Serena Yeung (2017). [http://cs231n.stanford.edu/slides/2017/cs231n_2017_lecture9.pdf Lecture 9: CNN Architectures] | 1 | |
| 22:13, 30 September 2018 | NIN Fig2.png (file) | 57 KB | Omoreira | Figure 2: The overall structure of Network In Network. In this paper the NINs include the stacking of three mlpconv layers and one global average pooling layer. In:Min Lin, Qiang Chen, and Shuicheng Yan (2013). [https://arxi... | 1 | |
| 22:12, 30 September 2018 | NIN Fig1.png (file) | 42 KB | Omoreira | Figure 1: Comparison of linear convolution layer and mlpconv layer. The linear convolution layer includes a linear filter while the mlpconv layer includes a micro network (we choose the multilayer perceptron in this paper).... | 1 | |
| 21:46, 30 September 2018 | GoogLeNet Szegedy 2014.png (file) | 76 KB | Omoreira | Figure 3: GoogLeNet network with all the bells and whistles.In: Christian Szegedy, Wei Liu, Yangqing Jia, Pierre Sermanet , Scott Reed , Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke, and Andrew Rabinovich... | 1 | |
| 12:12, 30 September 2018 | AlexNet 2012.png (file) | 73 KB | Omoreira | Figure 2: An illustration of the architecture of our CNN, explicitly showing the delineation of responsibilities between the two GPUs. One GPU runs the layer-parts at the top of the figure while the other runs the [[NN Layer|la... | 1 | |
| 11:38, 30 September 2018 | Alexnet Bhattacharyya2018.png (file) | 161 KB | Omoreira | Fig. 5: Detailed architecture of AlexNet as implemented in Python (top left), AlexNet implemented in MATLAB (top right) and the modified MATLAB layers (bottom). The dropout layers (not shown in the top left) are inserted after t... | 1 | |
| 23:09, 23 September 2018 | Rao et al 2013 Algprithm1.png (file) | 67 KB | Omoreira | Nikhil Rao, Parikshit Shah, Stephen Wright, and Robert Nowak (2013, May). [http://nikrao.github.io/Publications_files/FOBA_ICASSP_SUBMITTED.pdf "A greedy forward-backward algorithm for atomic norm constrained minimization"]. In [https:/... | 1 | |
| 22:31, 23 September 2018 | AIMA Algorithm15 4.png (file) | 65 KB | Omoreira | Retrieved from: http://aima.cs.berkeley.edu/algorithms.pdf | 1 | |
| 21:40, 23 September 2018 | Collins 2013 fig1.png (file) | 57 KB | Omoreira | Figure 1: The forward-backward algorithm. In: Michael Collins. (2013). [http://www.cs.columbia.edu/~mcollins/courses/6998-2012/notes/fb.pdf "The Forward-backward Algorithm"]. Columbia Columbia Univ | 1 | |
| 19:51, 2 September 2018 | 14047828 Alg551.png (file) | 69 KB | Omoreira | In: Jurgen Schmidhuber (2015). [https://arxiv.org/pdf/1404.7828.pdf "Deep learning in neural networks: An overview"]. Neural networks, 61, 85-117. [https://doi.org/10.1016/j.neunet.2014.09.003 DOI: 10.1016/j.neunet.2014.09.003] [https://arxiv.org/... | 1 | |
| 02:08, 13 August 2018 | Szegedy Toshev Erhan 2013 Fig2.png (file) | 117 KB | Omoreira | Figure 2: After regressing to object masks across several scales and large image boxes, we perform object box extraction. The obtained boxes are refined by repeating the same procedure on the sub images, cropped via the current o... | 1 | |
| 02:08, 13 August 2018 | Szegedy Toshev Erhan 2013 Fig1.png (file) | 69 KB | Omoreira | Figure 1: A schematic view of object detection as DNN-based regression. In: Christian Szegedy, Alexander Toshev, and Dumitru Erhan (2013). [https://pdfs.semanticscholar.org/713f/73ce5c3013d9fb796c21b981dc6629af0bd5.pdf "Deep neu... | 1 | |
| 01:55, 13 August 2018 | Dahl et al 2012 Fig1.png (file) | 140 KB | Omoreira | Fig. 1. Diagram of our hybrid architecture employing a deep neural network. The HMM models the sequential property of the speech signal, and the DNN models the scaled observation likelihood of all the senones (tied tri-phone sta... | 1 | |
| 01:24, 13 August 2018 | Hinton Deng Yu et al 2012 Fig1.png (file) | 34 KB | Omoreira | [FIG1] The sequence of operations used to create a DBN with three hidden layers and to convert it to a pretrained DBN-DNN. First, a GRBM is trained to model a window of frames of [[real-valued acoustic co... | 1 | |
| 00:23, 13 August 2018 | Jozefowicz et al 2016 Fig1.png (file) | 30 KB | Omoreira | <i>Figure 1</i>. A high-level diagram of the models presented in this paper. (a) is a standard LSTM LM. (b) represents an LM where both input and Softmax embeddi... | 1 | |
| 21:06, 12 August 2018 | Hinton Salakhutdinov 2006 Fig1.png (file) | 104 KB | Omoreira | <B>Fig. 1.</B> Pretraining consists of learning a stack of restricted Boltzmann machines (RBMs), each having only one layer of feature detectors. The learned feature activations of one RBM are used as the ‘‘[[da... | 1 | |
| 22:52, 5 August 2018 | Kim2018 Fig3 3.png (file) | 42 KB | Omoreira | Figure 3.3: Residual network, showing only the CNN architecture. In:Kyungna Kim (2018). [https://www2.eecs.berkeley.edu/Pubs/TechRpts/2018/EECS-2018-80.pdf "Arrhythmia Classification in Multi-Channel ECG Signals Using Deep Neural Networks"]. | 1 | |
| 22:50, 5 August 2018 | Kim2018 Fig3 4.png (file) | 63 KB | Omoreira | Figure 3.4: Combined LSTM-CNN model (LSTM portion may be uni- or bidirectional). In: Kyungna Kim (2018). [https://www2.eecs.berkeley.edu/Pubs/TechRpts/2018/EECS-2018-80.pdf "Arrhythmia Classification in Multi-Channel ECG Signals Using Deep... | 1 | |
| 22:30, 5 August 2018 | Kim2018 Fig3 2.png (file) | 54 KB | Omoreira | Figure 3.2: Bidirectional LSTM network with 2 stacked layers In: Kyungna Kim (2018). [https://www2.eecs.berkeley.edu/Pubs/TechRpts/2018/EECS-2018-80.pdf "Arrhythmia Classification in Multi-Channel ECG Signals Using Deep Neural Networks"]. | 1 | |
| 16:39, 5 August 2018 | Bentley1975 Fig1b.png (file) | 17 KB | Omoreira | Fig1b Jon Louis Bentley (1975). [http://cgi.di.uoa.gr/~ad/MDE515/p509-bentley.pdf "Multidimensional binary search trees used for associative searching"]. Communications of the ACM, 18(9), 509-517. [https://doi.org/10.1145/361002.361007 DOI:10.1145/... | 1 | |
| 16:38, 5 August 2018 | Bentley1975 Fig1a.png (file) | 20 KB | Omoreira | Fig1. Jon Louis Bentley (1975). [http://cgi.di.uoa.gr/~ad/MDE515/p509-bentley.pdf "Multidimensional binary search trees used for associative searching"]. Communications of the ACM, 18(9), 509-517. [https://doi.org/10.1145/361002.361007 DOI:10.1145... | 1 | |
| 23:03, 29 July 2018 | 1801.02143 Fig5.png (file) | 159 KB | Omoreira | Fig. 5: SBU-LSTMs architecture necessarily consists of a BDLSTM layer and a LSTM layer. Masking layer for handling missing values and multiple [[LSTM]... | 1 | |
| 21:29, 29 July 2018 | VGG1619.png (file) | 43 KB | Omoreira | In: Andrea Vedaldi, Karel Lenc, and Joao Henriques (2016). [https://www.robots.ox.ac.uk/~vgg/practicals/cnn-reg/#vgg-cnn-practical-image-regression VGG CNN Practical: Image Regression] | 1 | |
| 21:06, 22 July 2018 | Malsburg 1973 Fig4.png (file) | 43 KB | Omoreira | '''Fig. 4'''. A small part of the simulated cortex, showing the hexagonal array of the E-cells (upper plane) and the I-cells (lower plane). The different symbols are used to designate those cells which are connected... | 1 | |
| 20:27, 22 July 2018 | Kohonen 1982 Tab1.png (file) | 49 KB | Omoreira | '''Table 1'''. Formation of frequency maps in Simulation 4. The resonators (20 in number) corresponded to second-order filters with quality factor Q=2.5 and resonant frequencies selected at random from the range [1,2]. The [[Tra... | 1 | |
| 20:26, 22 July 2018 | Kohonen 1982 Fig6.png (file) | 47 KB | Omoreira | '''Fig. 6'''. Illustration of the one-dimensional system used in the selforganized formation of a frequency map. In:Teuvo Kohonen (1982). [https://cioslab.vcu.edu/alg/Visualize/kohonen-82.pdf "Self-Organized Formation of Topologically... | 1 | |
| 18:32, 22 July 2018 | Fukushima 1988 Fig7.png (file) | 149 KB | Omoreira | Figure 7. One-dimensional view of interconnections between cells of different cell-planes. Only one cell-plane is drawn in each layer.<P> In: [[Kunih... | 1 | |
| 01:28, 22 July 2018 | Krizhevsky et al 2012 CNN Fig2.png (file) | 80 KB | Omoreira | Figure 2: An illustration of the architecture of our CNN, explicitly showing the delineation of responsibilities between the two GPUs. One GPU runs the layer-parts at the top of the figure while the other runs the layer-parts at the bottom.... | 1 | |
| 01:08, 22 July 2018 | Lawrence at al FaceRecognition Fig5.png (file) | 276 KB | Omoreira | Fig. 5. A typical convolutional network. In: Steve Lawrence, C. Lee Giles, Ah Chung Tsoi, and Andrew D. Back. (1997). [http://www.cs.cmu.edu/afs/cs/user/bhiksha/WWW/courses/deeplearning/Fall.2016/pdfs/Lawrence_et_al.pdf "Face Recogn... | 1 | |
| 21:43, 15 July 2018 | Graves PhDthesis Fig3.4.png (file) | 50 KB | Omoreira | Figure 3.4: <B>Standard and bidirectional RNNs</B> In: Alex Graves (2008). [http://www.cs.toronto.edu/~graves/phd.pdf "Supervised Sequence Labelling with Recurrent Neural Networks", PhD Thesis] | 1 | |
| 19:50, 15 July 2018 | wang 2016 slide19.png (file) | 220 KB | Omoreira | In: Tingwu Wang (2016) Recurrent Neural Network Tutorial: http://www.cs.toronto.edu/~tingwuwang/rnn_tutorial.pdf | 1 | |
| 22:11, 8 July 2018 | LSTM Gers 2002 Fig1.png (file) | 91 KB | Omoreira | * (Gers et al., 2002) ⇒ Felix A. Gers, Nicol N. Schraudolph, and Jurgen Schmidhuber (2002). [http://www.jmlr.org/papers/volume3/gers02a/gers02a.pdf "Learning precise timing with LSTM recurrent networks"]. Journal of machine learnin... | 1 | |
| 21:52, 8 July 2018 | LSTM Hochreiter Schmidhuber 1997 Fig1.png (file) | 60 KB | Omoreira | * (Hochreiter & Schmidhuber,1997) ⇒ Sepp Hochreiter and Jourgen Schmidhuber (1997). [http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.676.4320&rep=rep1&type=pdf "Long short-term memory"]. Neural computation, 9(8), 1735-1780. **... | 1 | |
| 21:01, 8 July 2018 | arxiv 1412.3555 Fig1.png (file) | 40 KB | Omoreira | * Chung et al., 2014) ⇒ Junyoung Chung, Caglar Gulcehre, KyungHyun Cho, and Yoshua Bengio. (2014). [https://arxiv.org/pdf/1412.3555.pdf "Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling"]. In: Proce... | 1 | |
| 22:48, 1 July 2018 | icassp2015 fanbo 1009 Fig3.png (file) | 25 KB | Omoreira | Fig 3 In: Bo Fan, Lijuan Wang, Frank K. Soong, and Lei Xie (2015, April). [https://www.microsoft.com/en-us/research/wp-content/uploads/2015/04/icassp2015_fanbo_1009.pdf "Photo-real talking head with deep bidirectional LSTM"]. In Aco... | 1 |