IBMIBM的历史可以追溯到电子计算机发展前的几十年,在电子计算机发展之前,它经营穿孔卡片数据处理设备。IBM于1911年6月15日在宾厄姆顿西几英里处的纽约恩迪科特作为CTR公司注册。三个独立公司合并建立了CTR公司,它们是:列表机公司(1896年创立于华盛顿)、计算表公司(1901年创建于俄亥俄州代顿)和国际时代唱片公司(1900年创办于纽约州恩迪科特)。
national conference on artificial intelligence, (2020)
We propose a projected gradient method to address the issue of discrete input space, adopt group lasso to enforce the sparsity of the distortion, and develop a regularization technique to further improve the success rate
Cited by64BibtexViews55Links
0
0
Shai Gretz, Roni Friedman, Edo Cohen-Karlik,Assaf Toledo,Dan Lahav,Ranit Aharonov,Noam Slonim
national conference on artificial intelligence, (2020)
We present a novel argument dataset labeled for point-wise quality, IBM-Rank-30k, containing 30,497 arguments
Cited by22BibtexViews21Links
0
0
national conference on artificial intelligence, (2020)
We investigate a novel problem of exploring local and global temporal dynamics for Multivariate time series forecasting with missing values
Cited by5BibtexViews48Links
0
0
national conference on artificial intelligence, (2020)
We find that the proposed approach is effective across different data modalities, model architectures and applications
Cited by3BibtexViews17Links
0
0
Deng Huang, Peihao Chen,Runhao Zeng, Qing Du,Mingkui Tan,Chuang Gan
AAAI, pp.11021-11028, (2020)
We addressed the challenging task of video question answering, which requires machines to answer questions about videos in a natural language form. Previous state-of-the-art methods attempt to apply spatio-temporal attention mechanism on video frame features without explicitly ...
Cited by3BibtexViews34Links
0
0
national conference on artificial intelligence, (2020)
Cited by2BibtexViews41Links
0
0
national conference on artificial intelligence, (2020)
We propose a novel zeroth-order natural gradient descent to achieve high query-efficiency in black-box adversarial attacks
Cited by1BibtexViews19Links
0
0
Yunan Ye, Hengzhi Pei, Boxin Wang,Pin-Yu Chen, Yada Zhu,Jun Xiao,Bo Li
national conference on artificial intelligence, (2020)
We propose State Augmented RL, a novel and generic stateaugmented reinforcement learning framework that can integrate heterogeneous data sources into standard RL training pipelines for learning Portfolio management strategies
Cited by1BibtexViews32Links
0
0
national conference on artificial intelligence, (2020)
We find that there is little consistency in the literature in how such metrics are calculated, and show that such inconsistencies can have a significant effect on the measured fidelity
Cited by1BibtexViews13Links
0
0
Procheta Sen,Debasis Ganguly
national conference on artificial intelligence, (2020)
The results on the subsampled data typically reflects on the fact that predictions under the presence of cognitive biases in data can lead to non-humane responses such as all women are afraid
Cited by1BibtexViews3Links
0
0
Liat Ein-Dor,Eyal Shnarch,Lena Dankin, Alon Halfon,Benjamin Sznajder, Ariel Gera, Carlos Alzate, Martin Gleize, Leshem Choshen,Yufang Hou,Yonatan Bilu,Ranit Aharonov
national conference on artificial intelligence, (2020)
We presented a first end-to-end ”working solution” for the argument retrieval task, showing that it attains remarkably high precision on a wide range of topics
Cited by1BibtexViews32Links
0
0
We propose the visual concept-metaconcept learner for bridging visual concept learning and metaconcept learning
Cited by1BibtexViews26Links
0
0
ACL, pp.4029-4039, (2020)
We showed that a domain expert can quickly come up with a short list of pro and con key points per topic, that would capture the gist of crowd-contributed arguments, even without being exposed to the arguments themselves
Cited by0BibtexViews24Links
0
0
ACL, pp.7073-7086, (2020)
The experiments suggest that the best results are achieved using JensenShannon similarity, for speeches that contain explicit responses and using conditional mutual-information on speeches that respond to the input speech in an implicit way
Cited by0BibtexViews51Links
0
0
We find the optimal pruning threshold value for the trade-off between the test accuracy on clean images and the attack success rate
Cited by0BibtexViews32Links
0
0
IEEE Transactions on Pattern Analysis and Machine Intelligence, no. 2 (2019): 502-508
We present the Moments in Time Dataset, a large-scale collection of three second videos covering a wide range of dynamic events involving different agents
Cited by125BibtexViews294
0
0
national conference on artificial intelligence, (2019)
It adopts a new and adaptive random full gradient estimation strategy to strike a balance between query counts and estimation errors, and features a decoder for attack dimension reduction and algorithmic convergence acceleration
Cited by62BibtexViews48Links
0
0
ICLR, (2019)
We find that the widely used vanilla quantization approaches suffer from unexpected issues — the quantized model is more vulnerable to adversarial attacks
Cited by37BibtexViews13Links
0
0
CoRR, (2019): 405-413
We presented a scalable algorithm for the fair k-median problem by applying the techniques from embedding to tree metrics and locally constructing fairlets in a near linear time
Cited by34BibtexViews46Links
0
0
IJCAI, (2019): 3961-3967
We first introduce an edge perturbation based topology attack framework that overcomes the difficulty of attacking discrete graph structure data from a first-order optimization perspective
Cited by29BibtexViews43Links
0
0
Keywords
Machine LearningNeural NetworksArtificial Neural NetworksComputer VisionConvolutionDeep Neural NetworkInteractive Image RetrievalTraining DataVisualization3-layer Perceptron Network
Authors
Noam Slonim
Paper 33
Ranit Aharonov
Paper 16
Pinyu Chen
Paper 16
Yonatan Bilu
Paper 11
Shiyu Chang
Paper 9
Sijia Liu
Paper 8
Benjamin Sznajder
Paper 8
Cho-Jui Hsieh
Paper 7
Roy Bar Haim
Paper 7