Everyone's talking about the fast.ai Massive Open Online Course (MOOC) so I decided to have a go at their 2019 deep learning course Practical Deep Learning for Coders, v3. I've always known some deep learning concepts/ideas (I've been in this field for about a year now, dealing mostly with computer vision), but never really understood some intuitions or explanations. I also understand that Jeremy Howard, Rachel Thomas and Sylvain Gugger (follow them on Twitter!) are influential people in the deep learning sphere (Jeremy has a lot of experience with Kaggle competitions), so I hope to gain new insights and intuitions, and some tips and tricks for model training from them. I have so much to learn from these folks.

Natural Language Processing is fast becoming Artificial Intelligence's new frontier which we all are using on daily basis – Siri, Google search, chatbots, automatic translation are just some examples. NLP can offer much more within your organization. We can combine together with your existing business applications tailor-made solution to analyze text, understand the conclusions without human effort, turn unstructured data into tabular data and much more.

Increased deployment of Artificial Intelligence around the world has torn open a very public and heated debate. While AI is being used to do things like sentence criminals, determine who should be hired and fired, and assess what loan rate you should be offered, it's also being leveraged to protect against poaching, detect illnesses sooner and more accurately, and shed new insights into fighting climate change. As we continue to develop AmandaAI here at TTT, we increasingly involve ourselves in the field. And as the technology continues to advance, we will continue to take on more and more clients who want to incorporate AI into their software. Since we're helping to create an AI-enabled future, we have a responsibility to explore what exactly that means.

To most of us, a 3-D-printed turtle just looks like a turtle; four legs, patterned skin, and a shell. But if you show it to a particular computer in a certain way, that object's not a turtle -- it's a gun. Objects or images that can fool artificial intelligence like this are called adversarial examples. Jessy Lin, a senior double-majoring in computer science and electrical engineering and in philosophy, believes that they're a serious problem, with the potential to trip up AI systems involved in driverless cars, facial recognition, or other applications. She and several other MIT students have formed a research group called LabSix, which creates examples of these AI adversaries in real-world settings -- such as the turtle identified as a rifle -- to show that they are legitimate concerns.

The United States Geological Survey confirmed with the Center for Data Innovation over email on July 22, 2019, that "1-meter DEMs are available or in progress for 45% of the country."

Transfer learning methods for reinforcement learning (RL) domains facilitate the acquisition of new skills using previously acquired knowledge. The vast majority of existing approaches assume that the agents have the same design, e.g. same shape and action spaces. In this paper we address the problem of transferring previously acquired skills amongst morphologically different agents (MDAs). For instance, assuming that a bipedal agent has been trained to move forward, could this skill be transferred on to a one-leg hopper so as to make its training process for the same task more sample efficient? We frame this problem as one of subspace learning whereby we aim to infer latent factors representing the control mechanism that is common between MDAs. We propose a novel paired variational encoder-decoder model, PVED, that disentangles the control of MDAs into shared and agent-specific factors. The shared factors are then leveraged for skill transfer using RL. Theoretically, we derive a theorem indicating how the performance of PVED depends on the shared factors and agent morphologies. Experimentally, PVED has been extensively validated on four MuJoCo environments. We demonstrate its performance compared to a state-of-the-art approach and several ablation cases, visualize and interpret the hidden factors, and identify avenues for future improvements.

Stochastic Gradient Descent (SGD) methods are prominent for training machine learning and deep learning models. The performance of these techniques depends on their hyperparameter tuning over time and varies for different models and problems. Manual adjustment of hyperparameters is very costly and time-consuming, and even if done correctly, it lacks theoretical justification which inevitably leads to "rule of thumb" settings. In this paper, we propose a generic approach that utilizes the statistics of an unbiased gradient estimator to automatically and simultaneously adjust two paramount hyperparameters: the learning rate and momentum. We deploy the proposed general technique for various SGD methods to train Convolutional Neural Networks (CNN's). The results match the performance of the best settings obtained through an exhaustive search and therefore, removes the need for a tedious manual tuning.

To make efficient use of limited spectral resources, we in this work propose a deep actor-critic reinforcement learning based framework for dynamic multichannel access. We consider both a single-user case and a scenario in which multiple users attempt to access channels simultaneously. We employ the proposed framework as a single agent in the single-user case, and extend it to a decentralized multi-agent framework in the multi-user scenario. In both cases, we develop algorithms for the actor-critic deep reinforcement learning and evaluate the proposed learning policies via experiments and numerical results. In the single-user model, in order to evaluate the performance of the proposed channel access policy and the framework's tolerance against uncertainty, we explore different channel switching patterns and different switching probabilities. In the case of multiple users, we analyze the probabilities of each user accessing channels with favorable channel conditions and the probability of collision. We also address a time-varying environment to identify the adaptive ability of the proposed framework. Additionally, we provide comparisons (in terms of both the average reward and time efficiency) between the proposed actor-critic deep reinforcement learning framework, Deep-Q network (DQN) based approach, random access, and the optimal policy when the channel dynamics are known.

We consider a distributed learning problem over multiple access channel (MAC) using a large wireless network. The computation is made by the network edge and is based on received data from a large number of distributed nodes which transmit over a noisy fading MAC. The objective function is a sum of the nodes' local loss functions. This problem has attracted a growing interest in distributed sensing systems, and more recently in federated learning. We develop a novel Gradient-Based Multiple Access (GBMA) algorithm to solve the distributed learning problem over MAC. Specifically, the nodes transmit an analog function of the local gradient using common shaping waveforms and the network edge receives a superposition of the analog transmitted signals used for updating the estimate. GBMA does not require power control or beamforming to cancel the fading effect as in other algorithms, and operates directly with noisy distorted gradients. We analyze the performance of GBMA theoretically, and prove that it can approach the convergence rate of the centralized gradient descent (GD) algorithm in large networks. Specifically, we establish a finite-sample bound of the error for both convex and strongly convex loss functions with Lipschitz gradient. Furthermore, we provide energy scaling laws for approaching the centralized convergence rate as the number of nodes increases. Finally, experimental results support the theoretical findings, and demonstrate strong performance of GBMA using synthetic and real data.

The palapes cadets are one of the uniform organizations in UiTM Perlis for extra-curricular activities. The palapes cadets arrange their organization in a hierarchy according to grade. Senior uniform officer (SUO) is the highest rank, followed by a junior uniform officer (JUO), sergeant, corporal, lance corporal, and lastly, cadet officer, which is the lowest rank. The palapes organization has several methods to measure performance toward promotion to a higher rank, whether individual performance or in a group. Cadets are selected for promotion based on demonstrated leadership abilities, acquired skills, physical fitness, and comprehension of information as measured through standardized testing. However, this method is too complicated when manually assessed by a trainer or coach. Therefore, this study will propose an expert system, which is one of the artificial intelligence techniques that can recognize the readiness and progression of a palapes cadet.