机器学习作为CS必修课程之一, 一般包括supervised learning监督学习, unsupervised learning 无监督学习和reinforcement learning(RL)增强学习3个大方向.
supervised learning通常需要学习linear regression, decision tree, SVM(support vector machine), logistic regression, naive bayes, random forest,
Neural Networks神经网络等内容.
深度学习deep learning是现在非常热门的方向, 需要学习CNN (convolution neural network), RNN (recurrent neural network)等网络架构. 知识点包括dropout, backpropagation, pooling, convolutional layer等. 深度学习现在已经广泛应用到计算机视觉 (computer vision) 和 NLP (自然语言处理).
unsupervised learning通常要学习principal component analysis (PCA), factor analysis, clustering algorithm such as K-means, EM (Expectation–maximization algorithm), GMM (gaussian mixture model)等.
reinforcement learning一般会学习Q-learning和Deep Q-learning.
Food Classification Challenge All assignment work must use the Python/Keras CIPA1 development environment. Deliverables The main purpose of this assignment is to introduce the student to the practical aspects of developing advanced deep learning based computer vision systems within the Python/Keras environment. The assignment is worth 40% of your overall module mark2. […]
deep learning代写：Food Classification Challenge Read More »
COMP9417 Assignment 2 – project topics 0: Self-proposed The objective of this topic is to propose a machine learning problem, source the dataset(s) and implement a method to solve it. This will typically come from an area of work or research of which you have some previous experience. Topic 0: Propose your own topic Task
机器学习代写：COMP9417 Assignment 2 Read More »
Assessed Learning Outcomes This second assessment aims at testing your ability to build up a predictive model based on probability distributions analyse a dataset to gain understanding of the data from within Python build up a regression model and evaluate it communicate your findin gs on your predictive model How to submit For this assignment,,
Lab. 4 Bayes’ Box and R. In this lab you will need to be able to make the Bayes’ Box for Binomial experiments. Objectives: Review classical methods Learn how the components of a Bayes’ box are constructed using R. Learn how to construct a Bayes’ box using an R function. Learn how to make graphical
R语言代写：Lab. 4 Bayes’ Box and R. Read More »
Machine Learning Theory (CSC 482A/581A) Problem Set 2 Instructions: You must write up your solutions individually. You may have high-level discussions with up to 2 other students registered in the course. If you discuss problems with others, include at the top of your submission: their names, V#’s, and the problems discussed. Your solutions should be
机器学习代写：CSC 482A/581A Problem Set 2 Read More »
Due: Submission materials: Assessment criteria: Marks: Overview School of Computing and Information Systems The University of Melbourne COMP90049 Knowledge Technologies, Semester 2 2017 Project 2: Identifying Tweets with Adverse Drug Reactions Stage I: 1pm (13h00 UTC+10), Wed 11 Oct 2017 Stage II: 1pm (13h00 UTC+10), Wed 18 Oct 2017 Stage I: Source code, README, Predictions;
机器学习代写：COMP90049 Knowledge Technologies Project 2 Read More »
Due: Submission materials: Assessment criteria: Marks: Overview School of Computing and Information Systems The University of Melbourne COMP90049 Knowledge Technologies, Semester 2 2017 Project 1: Lexical Normalisation of Twitter Data 1pm (13h00 UTC+10), Wed 06 Sep 2017 Source code, README; PDF Report (Submission mechanisms described on the LMS) Method, Critical Analysis, Report Quality The Project
机器学习代写：COMP90049 Knowledge Technologies Project 1 Read More »
ASK 2 DESCRIPTION Search advertising has been one of the major revenue sources of the Internet industry for years. A key technology behind search advertising is to predict the click-through rate (pCTR) of ads, as the economic model behind search advertising requires pCTR values to rank ads and to price clicks. In this task, given
Introduction COMP9444 Neural Networks and Deep Learning Session 2, 2017 Project 3 – Deep Reinforcement Learning Due: Sunday 29 October, 23:59 pm Marks: 15% of final assessment In this assignment we will implement a Deep Reinforcement Learning algorithm on some classic control tasks in the OpenAI AI-Gym Environment. Specifically, we will implement Q-Learning using a
深度学习增强学习代写：COMP9444 Project 3 – Deep Reinforcement Learning Read More »
Introduction COMP9444 Neural Networks and Deep Learning Session 2, 2017 Project 2 – Recurrent Networks and Sentiment Classification Due Dates: Stage 1: Sunday 8 October, 23:59 pm Stage 2: Sunday 15 October, 23:59 pm Marks: 15% of final assessment You should now have a good understanding of the internal dynamics of TensorFlow and how to
神经网络深度学习代写：COMP9444 Neural Networks and Deep Learning Read More »