Christopher J. Gatti

Learn More
BACKGROUND The clinical outcome is generally positive for patients with node-negative breast carcinoma (i.e., those who do not have detectable metastases in the lymph nodes) who have been treated with surgery or surgery plus radiation therapy. In about 30% of the patients, however, the disease recurs, and they are at risk of death. Determination of valid(More)
CA15.3 preoperatory serum levels have been determined in 667 patients with primary untreated breast cancer and in 193 controls. The relationships between CA15.3 and several clinical and pathological parameters were evaluated. CA15.3 levels showed a highly significant direct relationship with stage, T, pT, N and the number of positive lymph nodes. The close(More)
To investigate whether sodium sensitivity of blood pressure participates in the relationship of arterial hypertension to chronic alcohol consumption, 30 alcoholics detoxified from 6 to 12 months and 30 teetotaler controls underwent a dietary sodium manipulation study. They received a daily 55 mmol sodium diet for 7 days, followed by a 260 mmol sodium diet(More)
The oestrogen induced pS2 protein was measured in the cytosol of 446 breast cancer samples by an immunoradiometric assay. The relationships between pS2 and several clinical and biological parameters were evaluated. pS2 was not correlated to age, pT and nodal status, while it was higher in pre- than in peri- and post-menopausal women. A statistically(More)
This study uses a design of experiments approach to understand the behavior of a neural network to learn the mountain car domain using the TD(λ) algorithm. A large experiment is first performed to characterize the probability of empirical convergence based on three parameters of the TD(λ) algorithm (λ, γ,), and a logistic regression model is fitted to this(More)
This work presents a simple implementation of reinforcement learning, using the temporal difference algorithm and a neural network, applied to the board game of Chung Toi, which is a challenging variation of Tic-Tac-Toe. The implementation of this learning algorithm is fully described and includes all parameter settings and various techniques to improve the(More)
This study investigates the content of the published scientific literature in the fields of operations research and management science (OR/MS) since the early 1950s. Our study is based on 80,757 published journal abstracts from 37 of the leading OR/MS journals. We have developed a topic model, using Latent Dirichlet Allocation (LDA), and extend this(More)
We use a reinforcement learning approach to learn a real world control problem, the truck backer-upper problem. In this problem, a tractor trailer truck must be backed into a loading dock from an arbitrary location and orientation. Our approach uses the temporal difference algorithm using a neural network as the value function approximator. The novelty of(More)