Machine learning qualifies computers to assimilate with data, without being solely programmed [1, 2]. Machine learning can be classified as supervised and unsupervised learning. In supervised learning, computers learn an objective that portrays an input to an output hinged on training input-output pairs [3]. Most efficient and widely used supervised learning algorithms are K-Nearest Neighbors (KNN), Support Vector Machine (SVM), Large Margin Nearest Neighbor (LMNN), and Extended Nearest Neighbor (ENN). The main contribution of this paper is to implement these elegant learning algorithms on eleven different datasets from the UCI machine learning repository to observe the variation of accuracies for each of the algorithms on all datasets. Analyzing the accuracy of the algorithms will give us a brief idea about the relationship of the machine learning algorithms and the data dimensionality. All the algorithms are developed in Matlab. Upon such accuracy observation, the comparison can be built among KNN, SVM, LMNN, and ENN regarding their performances on each dataset.

Abstract--We study stochastic multi-armed bandits with many players. The players do not know the number of players, cannot communicate with each other and if multiple players select a common arm they collide and none of them receive any reward. We consider the static scenario, where the number of players remains fixed, and the dynamic scenario, where the players enter and leave at any time. We provide algorithms based on a novel'trekking approach' that guarantees constant regret for the static case and sub-linear regret for the dynamic case with high probability. The trekking approach eliminates the need to estimate the number of players resulting in fewer collisions and improved regret performance compared to the state-of-theart algorithms. We also develop an epoch-less algorithm that eliminates any requirement of time synchronization across the players provided each player can detect the presence of other players on an arm. We validate our theoretical guarantees using simulation based and real test-bed based experiments. Multi-player multi-armed bandits (MPMAB) is a variant of the stochastic multi-armed bandits [1]-[3] where multiple players aim to maximize sum of their rewards playing the same set of arms. In this setting, the players do not communicate with each other and may not know number of other players in the game. If two or more players select the same arm simultaneously, they experience'collision' and none of them receive any reward. Our goal in this work is to develop distributed algorithms that aim to achieve high total rewards while keeping the number of collisions as low as possible. The study of MPMAB is mainly motivated from the ad-hoc cognitive radio networks (CRN) where multiple users transmit on a common set of channels (unlicensed spectrum) without any communication among them [4], [5]. Due to the ad hoc nature of such networks, a central controller, or a common control channels for coordination, may not be available and all channel selection decisions have to be done in a decentralized fashion [4]-[6]. Such models are being envisioned for futuristic ultra-dense wireless communication networks that can offer very high peak rates [7]. The quality of the channels are unknown to the users and their goal is to maximize number of successful transmissions (or sum rate/ throughput) in the network.

Coordinating agents to complete a set of tasks with intercoupled temporal and resource constraints is computationally challenging, yet human domain experts can solve these difficult scheduling problems using paradigms learned through years of apprenticeship. A process for manually codifying this domain knowledge within a computational framework is necessary to scale beyond the "single-expert, single-trainee" apprenticeship model. However, human domain experts often have difficulty describing their decision-making processes. We propose a new approach for capturing this decision-making process through counterfactual reasoning in pairwise comparisons. Our approach is model-free and does not require iterating through the state space. We demonstrate that this approach accurately learns multifaceted heuristics on a synthetic and real world data sets. We also demonstrate that policies learned from human scheduling demonstration via apprenticeship learning can substantially improve the efficiency of schedule optimization. We employ this human-machine collaborative optimization technique on a variant of the weapon-to-target assignment problem. We demonstrate that this technique generates optimal solutions up to 9.5 times faster than a state-of-the-art optimization algorithm.

Reading comprehension QA tasks have seen a recent surge in popularity, yet most works have focused on fact-finding extractive QA. We instead focus on a more challenging multi-hop generative task (NarrativeQA), which requires the model to reason, gather, and synthesize disjoint pieces of information within the context to generate an answer. This type of multi-step reasoning also often requires understanding implicit relations, which humans resolve via external, background commonsense knowledge. We first present a strong generative baseline that uses a multi-attention mechanism to perform multiple hops of reasoning and a pointer-generator decoder to synthesize the answer. This model performs substantially better than previous generative models, and is competitive with current state-of-the-art span prediction models. We next introduce a novel system for selecting grounded multi-hop relational commonsense information from ConceptNet via a pointwise mutual information and term-frequency based scoring function. Finally, we effectively use this extracted commonsense information to fill in gaps of reasoning between context hops, using a selectively-gated attention mechanism. This boosts the model's performance significantly (also verified via human evaluation), establishing a new state-of-the-art for the task. We also show that our background knowledge enhancements are generalizable and improve performance on QAngaroo-WikiHop, another multi-hop reasoning dataset.

We consider a problem of learning a reward and policy from expert examples under unknown dynamics in high-dimensional scenarios. Our proposed method builds on the framework of generative adversarial networks and exploits reward shaping to learn near-optimal rewards and policies. Potential-based reward shaping functions are known to guide the learning agent whereas in this paper we bring forward their benefits in learning near-optimal rewards. Our method simultaneously learns a potential-based reward shaping function through variational information maximization along with the reward and policy under the adversarial learning formulation. We evaluate our method on various high-dimensional complex control tasks. We also evaluate our learned rewards in transfer learning problems where training and testing environments are made to be different from each other in terms of dynamics or structure. Our experimentation shows that our proposed method not only learns near-optimal rewards and policies matching expert behavior, but also performs significantly better than state-of-the-art inverse reinforcement learning algorithms.

Einstein once said that if you judge a fish by its ability to climb a tree, it'll live its whole life thinking it's stupid. What you may not know is that he was referring to the public educational system and the one size fits all approach to teaching. Although more than a century passed since he said this, traditional models of education still exist till this day and still insist on standardized teaching techniques, despite their inability to deliver the best results. More and more learners -- in the academic and business world -- don't find these models challenging and engaging, so they're searching for alternatives, they want more personalized learning experiences. Personalized learning is the tailoring of learning environments with the primary focus on learners and how they experience the process of knowledge acquisition.

So instead, I've put this video together showing my code running. Topics covered broadly follow the course contents: * Linear Regression * Logistic Regression * Regularization * Hand-writing Recognition * Neural Networks * Support Vector Machines * Unsupervised Learning * Anomaly Detection * Recommender Systems Thanks for watching!

A few months ago I had the opportunity to complete Andrew Ng's Machine Learning MOOC taught on Coursera. It serves as a very good introduction for anyone who wants to venture into the world of AI/ML. I always wondered how amazing this course could be if it were in Python. I finally decided to re-take the course but only this time I would be completing the programming assignments in Python. In these series of blog posts, I plan to write about the Python version of the programming exercises used in the course.

Cheat sheets for machine learning are plentiful. Quality, concise technical cheat sheets, on the other hand... not so much. A good set of resources covering theoretical machine learning concepts would be invaluable. Shervine Amidi, graduate student at Stanford, and Afshine Amidi, of MIT and Uber, have created just such a set of resources. The VIP cheat sheets, as Shervine and Afshine have dubbed them (Github repo with PDFs available here), are structured around covering key top-level topics in Stanford's CS 229 Machine Learning course, including: You can visit Shervine's CS 229 resource page or the Github repo for more information, or can download the cheat sheets from the direct download links above.

Joy Buolamwini was a graduate student at MIT a few years ago when she was working on an art and science project called the Aspire Mirror. The set up was supposed to use readily available facial recognition software to project images onto people's faces. But the software couldn't identify African-American Buolamwini's own face--unless she put on a white mask. She tells the story in more detail in a TED talk. As she encountered other examples of what's become known as algorithmic bias, Buolamwini decided to conduct a more rigorous review.