Recently I wrote a blog titled "Pneumonia Detection From X-ray Images Using Deep Learning Neural Network" where I presented the results of what I chose to be the best out of 15 different model architectures that I created to solve a binary classification problem. For the readers not familiar with this, what it means is that my model will predict only a "0" or a "1". Before I continue, don't worry if you have not read my previous blog, you won't need it to understand this one as this will have all the necessary information to compare as the title says, a complex to a simple model. On my previous blog I described how I started with a simple 2-layer Convolutional Neural Network (CNN) model using minimal parameters to account for overfitting, and ended up with a more complex architecture made out of 5 convolutional blocks, each one, with dual layers and with some hyper-parameters to tune the model. This last model I called it Model_15, which resulted with a validation and Test accuracy of 94.83 and 90.84% respectively.

Looks like an interesting tool but without traditional wet-lab experiments why should chemists believe your suggestions? While a good chemist can often come up with a reasonable explanation why a change helps after seeing changes in assay results (e.g. If you want to try get a compound made and tested perhaps contact the team at Covid Moonshot and see if there's a feasible use case. My PI (one of the leads) says they're always interested in new candidates/triage strategies. Another issue might be that the synthetic accessibility of your candidates after large numbers of augmentation steps may become low.

If you are reading this article, I am sure that we share similar interests and are/will be in similar industries. So let's connect via Linkedin! Please do not hesitate to send a contact request! If you have recently started learning machine learning, you might have already realized the power of artificial neural networks and deep learning compared to traditional machine learning. Compared to other models, artificial neural networks require an extra set of technical skills and conceptual knowledge.

An artificial neural network is a biologically inspired computational model that is patterned after the network of neurons present in the human brain. Artificial neural networks can also be thought of as learning algorithms that model the input-output relationship. Applications of artificial neural networks include pattern recognition and forecasting in fields such as medicine, business, pure sciences, data mining, telecommunications, and operations managements. An artificial neural network transforms input data by applying a nonlinear function to a weighted sum of the inputs. The transformation is known as a neural layer and the function is referred to as a neural unit.

We investigate a deep reinforcement learning (RL) architecture that supports explaining why a learned agent prefers one action over another. The key idea is to learn action-values that are directly represented via human-understandable properties of expected futures. This is realized via the embedded self-prediction (ESP)model, which learns said properties in terms of human provided features. Action preferences can then be explained by contrasting the future properties predicted for each action. To address cases where there are a large number of features, we develop a novel method for computing minimal sufficient explanations from anESP. Our case studies in three domains, including a complex strategy game, show that ESP models can be effectively learned and support insightful explanations.

In this paper, we introduce a novel conditional generative adversarial network that creates dense 3D point clouds, with color, for assorted classes of objects in an unsupervised manner. To overcome the difficulty of capturing intricate details at high resolutions, we propose a point transformer that progressively grows the network through the use of graph convolutions. The network is composed of a leaf output layer and an initial set of branches. Every training iteration evolves a point vector into a point cloud of increasing resolution. After a fixed number of iterations, the number of branches is increased by replicating the last branch. Experimental results show that our network is capable of learning and mimicking a 3D data distribution, and produces colored point clouds with fine details at multiple resolutions.

In this paper, we investigate the following two limitations for the existing distractor generation (DG) methods. First, the quality of the existing DG methods are still far from practical use. There is still room for DG quality improvement. Second, the existing DG designs are mainly for single distractor generation. However, for practical MCQ preparation, multiple distractors are desired. Aiming at these goals, in this paper, we present a new distractor generation scheme with multi-tasking and negative answer training strategies for effectively generating \textit{multiple} distractors. The experimental results show that (1) our model advances the state-of-the-art result from 28.65 to 39.81 (BLEU 1 score) and (2) the generated multiple distractors are diverse and show strong distracting power for multiple choice question.

Relational databases are among the most widely used architectures to store massive amounts of data in the modern world. However, there is a barrier between these databases and the average user. The user often lacks the knowledge of a query language such as SQL required to interact with the database. The NL2SQL task aims at finding deep learning approaches to solve this problem by converting natural language questions into valid SQL queries. Given the sensitive nature of some databases and the growing need for data privacy, we have presented an approach with data privacy at its core. We have passed RoBERTa embeddings and data-agnostic knowledge vectors into LSTM based submodels to predict the final query. Although we have not achieved state of the art results, we have eliminated the need for the table data, right from the training of the model, and have achieved a test set execution accuracy of 76.7%. By eliminating the table data dependency while training we have created a model capable of zero shot learning based on the natural language question and table schema alone.

This paper presents a deep learning framework based on Long Short-term Memory Network(LSTM) that predicts price movement of cryptocurrencies from trade-by-trade data. The main focus of this study is on predicting short-term price changes in a fixed time horizon from a looking back period. By carefully designing features and detailed searching for best hyper-parameters, the model is trained to achieve high performance on nearly a year of trade-by-trade data. The optimal model delivers stable high performance(over 60% accuracy) on out-of-sample test periods. In a realistic trading simulation setting, the prediction made by the model could be easily monetized. Moreover, this study shows that the LSTM model could extract universal features from trade-by-trade data, as the learned parameters well maintain their high performance on other cryptocurrency instruments that were not included in training data. This study exceeds existing researches in term of the scale and precision of data used, as well as the high prediction accuracy achieved.

Graphs have been widely adopted to denote structural connections between entities. The relations are in many cases heterogeneous, but entangled together and denoted merely as a single edge between a pair of nodes. For example, in a social network graph, users in different latent relationships like friends and colleagues, are usually connected via a bare edge that conceals such intrinsic connections. In this paper, we introduce a novel graph convolutional network (GCN), termed as factorizable graph convolutional network (FactorGCN), that explicitly disentangles such intertwined relations encoded in a graph. FactorGCN takes a simple graph as input, and disentangles it into several factorized graphs, each of which represents a latent and disentangled relation among nodes. The features of the nodes are then aggregated separately in each factorized latent space to produce disentangled features, which further leads to better performances for downstream tasks. We evaluate the proposed FactorGCN both qualitatively and quantitatively on the synthetic and real-world datasets, and demonstrate that it yields truly encouraging results in terms of both disentangling and feature aggregation.