Zobrazeno 1 - 10
of 1 380
pro vyhledávání: '"Allen, Carl"'
In self-supervised learning (SSL), representations are learned via an auxiliary task without annotated labels. A common task is to classify augmentations or different modalities of the data, which share semantic content (e.g. an object in an image) b
Externí odkaz:
http://arxiv.org/abs/2402.01399
We present a latent variable model for classification that provides a novel probabilistic interpretation of neural network softmax classifiers. We derive a variational objective to train the model, analogous to the evidence lower bound (ELBO) used to
Externí odkaz:
http://arxiv.org/abs/2305.10406
Large language models appear to learn facts from the large text corpora they are trained on. Such facts are encoded implicitly within their many parameters, making it difficult to verify or manipulate what knowledge has been learned. Language models
Externí odkaz:
http://arxiv.org/abs/2210.13617
Autor:
Miladinović, Đorđe, Shridhar, Kumar, Jain, Kushal, Paulus, Max B., Buhmann, Joachim M., Sachan, Mrinmaya, Allen, Carl
In principle, applying variational autoencoders (VAEs) to sequential data offers a method for controlled sequence generation, manipulation, and structured representation learning. However, training sequence VAEs is challenging: autoregressive decoder
Externí odkaz:
http://arxiv.org/abs/2209.12590
Autor:
Allen, Carl
Representing words by vectors, or embeddings, enables computational reasoning and is foundational to automating natural language tasks. For example, if word embeddings of similar words contain similar values, word similarity can be readily assessed,
Externí odkaz:
http://arxiv.org/abs/2202.00486
Autor:
Weinstein, Joanna, Hinson, Ashley P., Allen, Carl E., Eckstein, Olive S., Gulati, Nitya, Chandrakasan, Shanmuganathan, Haines, Hilary, Nakano, Taizo, Patel, Sachit A., Behrens, Edward M, Intzes, Stefanos, Hays, Allyson, Dávila Saldaña, Blachy, Jordan, Michael B., Zoref-Lorenz, Adi, Hanna, Rabi, Isakoff, Michael, Ray, Anish K., Rothman, Jennifer, Tandra, Anand, Cooper, Robert, Leiding, Jennifer W., Chien, May, Sarangi, Susmita, Gidvani, Diaz, Satwani, Prakesh, Carter, John, Henry, Michael, Gloude, Nicholas, Bhatt, Sima, Bhatla, Deepika, Draper, Lauren, Panigrahi, Arun, Hermiston, Michelle, Modica, Renee, Riskalla, Mona, Baker, Ashley, Ward, Brant, Behrens, Edward M., Henry, Michael M., Hermiston, Michelle L., Oladapo, Abiola, Pednekar, Priti, Sarangi, Susmita N., Walkovich, Kelly J., Yee, John D.
Publikováno v:
In Blood Advances 14 May 2024 8(9):2248-2258
Autor:
Deng, Qing, Lakra, Priya, Gou, Panhong, Yang, Haopeng, Meydan, Cem, Teater, Matthew, Chin, Christopher, Zhang, Wenchao, Dinh, Tommy, Hussein, Usama, Li, Xubin, Rojas, Estela, Liu, Weiguang, Reville, Patrick K., Kizhakeyil, Atish, Barisic, Darko, Parsons, Sydney, Wilson, Ashley, Henderson, Jared, Scull, Brooks, Gurumurthy, Channabasavaiah, Vega, Francisco, Chadburn, Amy, Cuglievan, Branko, El-Mallawany, Nader Kim, Allen, Carl, Mason, Christopher, Melnick, Ari, Green, Michael R.
Publikováno v:
In Cancer Cell 8 April 2024 42(4):605-622
Autor:
Wistinghausen, Birte, Toner, Keri, Barkauskas, Donald A., Jerkins, Lauren P, Kinoshita, Hannah, Chansky, Pamela, Pezzella, Gloria, Saguilig, Lauren, Hayashi, Robert J., Abhyankar, Harshal, Scull, Brooks, Karri, Vivekanudeep, Tanna, Jay, Hanley, Patrick, Hermiston, Michelle L., Allen, Carl E., Bollard, Catherine M.
Publikováno v:
In Blood Advances 12 March 2024 8(5):1116-1127
As data volumes continue to grow, the labelling process increasingly becomes a bottleneck, creating demand for methods that leverage information from unlabelled data. Impressive results have been achieved in semi-supervised learning (SSL) for image c
Externí odkaz:
http://arxiv.org/abs/2007.02745